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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     standardized
    -0.07
    補
    -0.07
    انات
    -0.07
     pien
    -0.07
     illeg
    -0.06
     Cette
    -0.06
     repet
    -0.06
    ارت
    -0.06
     Yin
    -0.06
     stature
    -0.06
    POSITIVE LOGITS
    fung
    0.07
    _Integer
    0.06
     burgl
    0.06
    (lbl
    0.06
    ژن
    0.06
     Graduate
    0.06
    krit
    0.06
    ancouver
    0.05
     股
    0.05
    emaker
    0.05
    Act Density 0.005%

    No Known Activations