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

    Neuronpedia

    INDEX
    Explanations

    many others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     undervalued
    0.46
     disen
    0.46
     lessening
    0.42
     dissatisf
    0.42
     detract
    0.42
    認為
    0.41
     Apesar
    0.41
     Although
    0.40
     modernity
    0.40
     melanch
    0.40
    POSITIVE LOGITS
     countless
    0.84
    有很多
    0.84
     ಅನೇಕ
    0.80
    无数
    0.79
     многочис
    0.74
     dozens
    0.73
     MANY
    0.73
     अनेक
    0.72
     అనేక
    0.72
     many
    0.71
    Act Density 0.295%

    No Known Activations