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

    Neuronpedia

    INDEX
    Explanations

    scores and results from lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Angaben
    0.75
    必备
    0.74
     getSize
    0.73
     처음
    0.73
    相结合
    0.70
     defaults
    0.70
    良かった
    0.70
    精力
    0.69
     Euclidean
    0.69
    ቃት
    0.68
    POSITIVE LOGITS
     from
    0.91
     across
    0.83
     over
    0.80
    から
    0.76
     agus
    0.75
     और
    0.75
     из
    0.75
     અને
    0.75
     and
    0.74
     から
    0.74
    Act Density 0.008%

    No Known Activations