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

    Neuronpedia

    INDEX
    Explanations

    Lists and sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    امی
    -0.07
     Мор
    -0.07
     Поч
    -0.07
     Yas
    -0.06
    customers
    -0.06
     ад
    -0.06
     �
    -0.06
     Я
    -0.06
    uct
    -0.06
    POSITIVE LOGITS
    _MULT
    0.08
    /Subthreshold
    0.07
    nout
    0.07
     journals
    0.06
    .Tensor
    0.06
     mesma
    0.06
    Arguments
    0.06
     ^=
    0.06
    علومات
    0.06
    xFFFFFF
    0.06
    Act Density 0.005%

    No Known Activations