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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash

    The neuron fires on formal license/disclaimer terms (e.g. “PROCUREMENT,” “EXEMPLARY,” etc.) found in open‐source license header blocks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ㅠㅠ
    -0.07
    aporation
    -0.07
    =Y
    -0.07
     gb
    -0.06
     کیفیت
    -0.06
     %%↵
    -0.06
    人们
    -0.06
    /net
    -0.06
    figures
    -0.06
     кас
    -0.06
    POSITIVE LOGITS
    <_
    0.07
    .scalar
    0.06
     сигн
    0.06
     μας
    0.06
    (klass
    0.06
    юр
    0.06
    Membership
    0.06
     infinity
    0.06
     Ave
    0.06
     βιβ
    0.06
    Act Density 0.001%

    No Known Activations