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

    Neuronpedia

    INDEX
    Explanations

    Fach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conservative
    -0.08
    러스
    -0.07
    aling
    -0.06
    anoia
    -0.06
    _AS
    -0.06
    ався
    -0.06
    izioni
    -0.06
     всп
    -0.06
     TR
    -0.06
     обл
    -0.06
    POSITIVE LOGITS
     Fach
    0.16
     предмет
    0.14
     Sach
    0.14
    sigmoid
    0.13
     sigmoid
    0.13
    igmoid
    0.12
     sach
    0.11
     LGPL
    0.10
     дет
    0.08
    mouth
    0.07
    Act Density 0.004%

    No Known Activations