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

    Neuronpedia

    INDEX
    Explanations

    questions and reasons related to various subjects

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

    "Why" or question related words

    np_acts-logits-general · gemini-2.0-flash

    asking why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.79
    IsMutable
    -0.73
     وتسجيلات
    -0.73
    SequentialGroup
    -0.72
    oneofs
    -0.67
     виправивши
    -0.67
     Савезне
    -0.66
     Audiodateien
    -0.66
     Infórmanos
    -0.66
    ValueStyle
    -0.65
    POSITIVE LOGITS
     why
    0.96
    why
    0.80
    Why
    0.78
    Почему
    0.76
     Why
    0.75
     mengapa
    0.69
     kenapa
    0.68
     waarom
    0.67
     warum
    0.67
    的原因
    0.66
    Act Density 0.210%

    No Known Activations