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

    Neuronpedia

    INDEX
    Explanations

    sentences that convey numerical data or statistics

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

    lists with periods or numbering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.90
    征詢我
    -0.79
    arangay
    -0.73
    tagHelperRunner
    -0.72
    SequentialGroup
    -0.71
    mpagne
    -0.71
     indígen
    -0.70
    httphttps
    -0.70
    новништво
    -0.69
    genodigd
    -0.69
    POSITIVE LOGITS
    <bos>
    0.59
    .
    0.59
    The
    0.56
    item
    0.53
    *
    0.47
     the
    0.44
    For
    0.43
    If
    0.43
    cdot
    0.43
     =
    0.42
    Act Density 0.042%

    No Known Activations