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

    Neuronpedia

    INDEX
    Explanations

    occurrences of formatting symbols and certain repeated words

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

    Text after periods, newlines, or special characters

    np_acts-logits-general · gemini-2.0-flash

    the terms, supplementary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    المكان
    -0.56
     VIAF
    -0.53
    lyt
    -0.52
    myModal
    -0.48
    EDEFAULT
    -0.48
    apie
    -0.48
    Попис
    -0.47
    onInit
    -0.47
    sizeCache
    -0.46
    قایناق‌لار
    -0.45
    POSITIVE LOGITS
    enumerate
    0.59
     للاسماء
    0.58
    __':
    0.58
    httphttps
    0.54
    __":
    0.54
    _));
    0.52
    "]]
    0.52
    ::_('
    0.52
    __':
    0.52
    "]];
    0.52
    Act Density 0.005%

    No Known Activations