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

    Neuronpedia

    INDEX
    Explanations

    file, File, Online Handle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kert
    0.94
    тур
    0.92
     Тур
    0.87
     parques
    0.84
     Kork
    0.82
     அறிக
    0.81
     オレンジ
    0.80
     Husk
    0.79
    ꯃ
    0.79
     Rational
    0.79
    POSITIVE LOGITS
    file
    0.98
    File
    0.97
     File
    0.92
     Wheeler
    0.88
     Friedman
    0.82
     file
    0.81
     Davidson
    0.79
     Guo
    0.79
     Leopold
    0.77
    Φ
    0.77
    Act Density 1.009%

    No Known Activations