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

    Neuronpedia

    INDEX
    Explanations

    **Input:** followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caractères
    0.49
     けれど
    0.48
     cioè
    0.47
     Veracruz
    0.46
     بُک
    0.45
     Jehová
    0.45
     éxitos
    0.44
     luật
    0.44
     乀
    0.43
    赋值
    0.43
    POSITIVE LOGITS
    :
    0.54
    epart
    0.45
    ि
    0.45
    க்க
    0.44
     gathered
    0.43
     standardized
    0.43
     all
    0.42
    ла
    0.42
    тельном
    0.42
    中
    0.42
    Act Density 0.004%

    No Known Activations