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

    Neuronpedia

    INDEX
    Explanations

    amin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     review
    -0.06
     مجموع
    -0.06
    Absolute
    -0.06
    -semibold
    -0.06
    ，因此
    -0.06
     روان
    -0.06
     кв
    -0.06
    Inicial
    -0.06
    Physical
    -0.06
    řiv
    -0.06
    POSITIVE LOGITS
     simd
    0.07
    agu
    0.07
    _TCP
    0.07
    nop
    0.07
    ạc
    0.06
    Ya
    0.06
    탕
    0.06
     Alle
    0.06
     takım
    0.06
    madı
    0.06
    Act Density 0.001%

    No Known Activations