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

    Neuronpedia

    INDEX
    Explanations

    crisis events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ucfirst
    -0.08
    مخاط
    -0.08
    🏯
    -0.07
     JADX
    -0.07
    keypress
    -0.07
    .Role
    -0.07
    ꦕ
    -0.07
    عزي
    -0.06
     offset
    -0.06
    nç
    -0.06
    POSITIVE LOGITS
     burst
    0.08
     siè
    0.07
    péri
    0.07
     om
    0.07
    葺
    0.07
    бри
    0.07
    #\
    0.06
     выбр
    0.06
     sí
    0.06
    Iter
    0.06
    Act Density 0.123%

    No Known Activations