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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lg
    -0.08
     Viol
    -0.07
    Viol
    -0.07
     phóng
    -0.07
    foreign
    -0.07
     printf
    -0.07
     sales
    -0.07
    事
    -0.06
    �
    -0.06
    Painter
    -0.06
    POSITIVE LOGITS
    usercontent
    0.08
    /as
    0.07
    ـــ
    0.06
     Aş
    0.06
    .math
    0.06
    má
    0.06
    _hdl
    0.06
     naší
    0.06
    /rest
    0.06
     proč
    0.06
    Act Density 0.003%

    No Known Activations