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

    Neuronpedia

    INDEX
    Explanations

    considered by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    变得
    0.67
    Become
    0.65
     станови
    0.59
     Become
    0.58
     صارت
    0.56
    变成
    0.56
     становится
    0.56
    显得
    0.55
    become
    0.55
    變成
    0.55
    POSITIVE LOGITS
     to
    0.95
     by
    0.93
     oleh
    0.72
     να
    0.70
     alongside
    0.69
     untuk
    0.66
     sebagai
    0.65
     doorways
    0.63
    by
    0.63
     ως
    0.63
    Act Density 0.045%

    No Known Activations