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

    Neuronpedia

    INDEX
    Explanations

    variety, variant, Rendite, external, not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.87
    ed
    0.76
    ли
    0.76
     detects
    0.76
    وث
    0.75
     મોટી
    0.73
    Луч
    0.73
    疯
    0.72
     accurate
    0.71
    ეც
    0.71
    POSITIVE LOGITS
     naal
    0.79
     anteriormente
    0.77
     élev
    0.75
     deceive
    0.75
    なかった
    0.74
     torne
    0.74
     então
    0.73
     nourrir
    0.73
    emente
    0.72
    Ụ
    0.71
    Act Density 0.000%

    No Known Activations