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

    Neuronpedia

    INDEX
    Explanations

    calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вновь
    -0.08
     снова
    -0.08
     mettant
    -0.08
     beautifully
    -0.07
     опять
    -0.07
    .strict
    -0.07
     sogen
    -0.07
     Теперь
    -0.07
    Again
    -0.07
     née
    -0.07
    POSITIVE LOGITS
     approximate
    0.11
     digest
    0.08
    中央値
    0.08
    슷
    0.08
    ertje
    0.08
     Approx
    0.07
    erval
    0.07
    平均
    0.07
    843
    0.07
     comparaison
    0.07
    Act Density 0.046%

    No Known Activations