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

    Neuronpedia

    INDEX
    Explanations

    explicit, unsafe, or illegal material

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ዘዴ
    0.39
     Movie
    0.37
     जिन
    0.37
     condiciones
    0.37
     condições
    0.36
    दर्शक
    0.36
     조건을
    0.36
    MovieDetails
    0.36
     ছবিটি
    0.36
    origines
    0.35
    POSITIVE LOGITS
     material
    2.41
    material
    1.95
     materiale
    1.91
     материала
    1.90
     материа
    1.85
     Material
    1.84
    Material
    1.83
     матеріа
    1.77
     MATERIAL
    1.75
     материал
    1.75
    Act Density 0.170%

    No Known Activations