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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Generates
    -0.10
    _DISPLAY
    -0.09
     Playlist
    -0.08
    .generated
    -0.08
     منتشر
    -0.08
     erklärt
    -0.08
     erklären
    -0.08
     Film
    -0.08
     hiện
    -0.08
     ಹಿಂದ
    -0.08
    POSITIVE LOGITS
     coverings
    0.08
     invocation
    0.07
    0.07
     ары
    0.07
     кры
    0.07
     viruses
    0.07
     guardians
    0.07
     можно
    0.07
    ísmo
    0.07
     рекомендации
    0.07
    Act Density 0.006%
    No Known Activations