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

    Neuronpedia

    INDEX
    Explanations

    try to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kul
    0.54
    ുള്ള
    0.43
    ्या
    0.41
     của
    0.40
    为了
    0.40
    रा
    0.40
    بة
    0.40
    那
    0.40
     Alan
    0.39
    든
    0.39
    POSITIVE LOGITS
    களில்
    0.46
     ニュー
    0.45
    ducers
    0.43
    FlatStyle
    0.42
    க்கழக
    0.42
    ivez
    0.42
    sizer
    0.41
    nerg
    0.41
     doświad
    0.41
    cG
    0.41
    Act Density 0.002%

    No Known Activations