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

    Neuronpedia

    INDEX
    Explanations

    información adicional o básica

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    者の
    0.63
    ます
    0.59
    ikiem
    0.59
    OutputFile
    0.59
    슐
    0.57
    umni
    0.57
    АТ
    0.55
    者は
    0.55
     individus
    0.54
     Государ
    0.54
    POSITIVE LOGITS
    i
    1.21
    ي
    1.13
    in
    0.97
    י
    0.88
     can
    0.84
    f
    0.77
    ie
    0.71
    iin
    0.71
    ి
    0.71
    he
    0.70
    Act Density 0.114%

    No Known Activations