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

    Neuronpedia

    INDEX
    Explanations

    central concept or point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    從小
    0.93
    רי
    0.86
    从小
    0.83
    юр
    0.76
     sebelumnya
    0.74
    ালিয়া
    0.73
     Side
    0.73
    കര
    0.72
     الري
    0.71
    ریق
    0.70
    POSITIVE LOGITS
    piece
    1.02
    pieces
    0.99
    ference
    0.91
    ymmetric
    0.82
     nervous
    0.81
    ymmetrical
    0.80
    pivot
    0.80
     név
    0.79
    nerv
    0.77
    Piece
    0.77
    Act Density 0.143%

    No Known Activations