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

    Neuronpedia

    INDEX
    Explanations

    canvas

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ناة
    0.75
    溱
    0.71
    UseDebug
    0.71
    鳌
    0.70
    大家的
    0.69
    тели
    0.69
    anées
    0.69
     nee
    0.68
     ಯಾವುದೇ
    0.67
     gorg
    0.67
    POSITIVE LOGITS
    映射
    0.73
    }_{[
    0.69
    setId
    0.67
    ิลป
    0.67
     mapping
    0.67
     mapped
    0.66
    стре
    0.66
     স্থাপ
    0.65
     setting
    0.63
     روی
    0.63
    Act Density 0.001%

    No Known Activations