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

    Neuronpedia

    INDEX
    Explanations

    Index numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     representing
    0.42
     scaled
    0.42
     range
    0.40
     calculated
    0.39
    range
    0.38
    woman
    0.38
    aq
    0.37
    agency
    0.37
    translated
    0.37
    imi
    0.37
    POSITIVE LOGITS
     Índ
    0.45
    𝟭
    0.43
    Indexs
    0.42
     კომ
    0.42
    𝟮
    0.42
     INDI
    0.41
    Indigo
    0.40
     ಇಂಡ
    0.40
    డ్
    0.39
     двадцать
    0.39
    Act Density 0.002%

    No Known Activations