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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    code related to color manipulation and conversions.

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

    The neuron fires on numeric literal tokens—especially floating‐point constants.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.07
    711
    -0.07
     Cater
    -0.06
    hů
    -0.06
     ㅡ
    -0.06
     erupt
    -0.06
     gratuito
    -0.06
    翔
    -0.06
    .cgi
    -0.06
     كه
    -0.06
    POSITIVE LOGITS
    PS
    0.08
     electronics
    0.07
    'action
    0.07
     stabilized
    0.07
    roe
    0.07
     UK
    0.06
    .credit
    0.06
     استاندارد
    0.06
     groundwork
    0.06
     prac
    0.06
    Act Density 0.013%

    No Known Activations