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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lions
    -0.07
    Nous
    -0.07
     Adoles
    -0.07
    odes
    -0.07
    _container
    -0.07
     males
    -0.07
    flutter
    -0.07
    riteria
    -0.07
    ashion
    -0.07
    nf
    -0.07
    POSITIVE LOGITS
    쐈
    0.07
    �
    0.07
    -reaching
    0.07
     بالإ
    0.06
     тыс
    0.06
    사업
    0.06
    ᵞ
    0.06
     gele
    0.06
     İş
    0.06
    [sub
    0.06
    Act Density 0.020%

    No Known Activations