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

    Neuronpedia

    INDEX
    Explanations

    youtube links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cod
    -0.77
    lencia
    -0.75
    ผ
    -0.73
    Wikimedia
    -0.73
    JavaScript
    -0.72
     gefe
    -0.69
    実行
    -0.68
    ା
    -0.68
    Voice
    -0.67
    дит
    -0.66
    POSITIVE LOGITS
    youtu
    1.00
     CYP
    0.83
    принима
    0.79
    ouin
    0.79
     lít
    0.71
     Ду
    0.71
     be
    0.71
    brero
    0.71
    сезон
    0.70
    роки
    0.69
    Act Density 0.044%

    No Known Activations