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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dens
    -0.08
    _Z
    -0.07
    Chelsea
    -0.07
    iến
    -0.06
     Tb
    -0.06
     carousel
    -0.06
     ieee
    -0.06
    "+
    -0.06
    χω
    -0.06
    -rounded
    -0.06
    POSITIVE LOGITS
     yaklaşık
    0.06
     تول
    0.06
    命
    0.06
    /ws
    0.06
    generation
    0.06
     привод
    0.06
    .EditValue
    0.06
    یک
    0.06
    ysical
    0.06
     lic
    0.06
    Act Density 0.009%

    No Known Activations