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

    Neuronpedia

    INDEX
    Explanations

    model starting response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hidden
    0.41
    commercial
    0.39
    Conceptual
    0.38
    需
    0.38
    Please
    0.38
     Software
    0.38
     commerciali
    0.38
     acceptor
    0.37
    Annex
    0.37
     comerciais
    0.37
    POSITIVE LOGITS
     absolutely
    0.43
     отлично
    0.41
     отлич
    0.41
     odlič
    0.40
    тный
    0.40
     абсолютно
    0.37
     Bauern
    0.37
    etics
    0.37
     मिक्स
    0.37
    Michelle
    0.37
    Act Density 0.105%

    No Known Activations