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

    Neuronpedia

    INDEX
    Explanations

    answer value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🛖
    0.72
     мальчика
    0.70
    lympi
    0.69
    na
    0.68
    🩶
    0.67
     ù
    0.66
    0.66
     पुष्प
    0.65
     NPTypeCode
    0.64
    <unused1052>
    0.64
    POSITIVE LOGITS
    ;
    0.55
    (
    0.54
    ות
    0.52
    斯坦
    0.51
    癌症
    0.50
    وندی
    0.50
    in
    0.49
     critic
    0.49
    ياء
    0.49
    :
    0.48
    Act Density 0.000%

    No Known Activations