Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Instructions/Descriptions

    np_max-act · gemini-2.0-flash

    technical descriptions of components and their functions in electrical or mechanical systems.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the little “instruction” words in patent‐style method steps—prepositions and verbs like “with,” “to laminate,” “into,” etc., that link components and actions in a procedural description.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Mana
    -0.07
    licas
    -0.06
    ﻨ
    -0.06
    ิทย
    -0.06
     Threshold
    -0.06
     infertility
    -0.06
     thank
    -0.06
     Thank
    -0.06
    atik
    -0.06
    -font
    -0.06
    POSITIVE LOGITS
    .erb
    0.07
     tmpl
    0.07
     creations
    0.07
     pollut
    0.06
     greater
    0.06
    .BASELINE
    0.06
     jMenuItem
    0.06
     bağımsız
    0.06
    Either
    0.06
     diamonds
    0.06
    Act Density 0.168%

    No Known Activations