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
     ಸಂಪ
    -0.08
     pore
    -0.08
     પૂર્ણ
    -0.08
     parties
    -0.07
     tinder
    -0.07
     Zillow
    -0.07
     સંપૂર્ણ
    -0.07
    isal
    -0.07
    ifix
    -0.07
     completed
    -0.07
    POSITIVE LOGITS
     reversing
    0.08
    .mp
    0.08
     reversed
    0.08
    ший
    0.08
    ницу
    0.08
     اخت
    0.08
    чика
    0.07
    коп
    0.07
    (child
    0.07
    agnitude
    0.07
    Act Density 0.014%

    No Known Activations