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

    Neuronpedia

    INDEX
    Explanations

    Dickens novels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .year
    -0.08
    hours
    -0.07
    _Data
    -0.07
    世界
    -0.07
    ۱۰
    -0.07
     пу
    -0.06
     gp
    -0.06
    ائی
    -0.06
    ца
    -0.06
    _SCOPE
    -0.06
    POSITIVE LOGITS
     담
    0.07
    няти
    0.06
     hatır
    0.06
     شکست
    0.06
     gchar
    0.06
    layın
    0.06
     break
    0.06
    regnum
    0.06
    ではない
    0.06
     especial
    0.05
    Act Density 0.004%

    No Known Activations