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

    Neuronpedia

    INDEX
    Explanations

    references to organizations or institutions related to clubs, parties, or community structures

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

    organizations or locations

    np_acts-logits-general · gemini-2.0-flash

    political and social entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.97
     Infórmanos
    -0.83
     @"/
    -0.79
    TagMode
    -0.77
    enumii
    -0.75
     autorytatywna
    -0.73
     ویکی‌پدی
    -0.73
    +#+
    -0.71
    -0.71
    haviors
    -0.70
    POSITIVE LOGITS
     itself
    0.94
    ’
    0.84
    '
    0.78
     inteiro
    0.57
     Itself
    0.52
     its
    0.49
    wide
    0.49
     μας
    0.47
    SuspendLayout
    0.46
    itself
    0.46
    Act Density 0.914%

    No Known Activations