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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    era
    -0.07
     cwd
    -0.07
    лих
    -0.07
    .inf
    -0.06
    χα
    -0.06
     Prozent
    -0.06
     тва
    -0.06
     Wholesale
    -0.06
    كل
    -0.06
     doctors
    -0.06
    POSITIVE LOGITS
     органів
    0.07
     accommod
    0.06
    .PostMapping
    0.06
     şehir
    0.06
    isz
    0.06
    ptrdiff
    0.06
    His
    0.06
     mommy
    0.06
    ožná
    0.06
     Ads
    0.06
    Act Density 0.019%

    No Known Activations