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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of “first N” counts—that is, ordinal phrases like “first two,” “first three,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ecuador
    -0.07
    systems
    -0.07
     hierarchical
    -0.06
     undefined
    -0.06
    อนไลน
    -0.06
     malware
    -0.06
    orca
    -0.06
     Stamina
    -0.06
    �
    -0.06
    Tower
    -0.06
    POSITIVE LOGITS
     TITLE
    0.07
    zek
    0.07
    .createElement
    0.07
     �
    0.06
    .ecore
    0.06
    [$_
    0.06
     науч
    0.06
     गत
    0.06
     XM
    0.06
    yms
    0.06
    Act Density 0.014%

    No Known Activations