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

    Neuronpedia

    INDEX
    Explanations

    in: an, or, real, Fish, the, complex, your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    1.59
    j
    1.47
    ம்
    1.25
    ць
    1.23
    ка
    1.19
    ев
    1.19
    ων
    1.15
    чный
    1.11
    نوان
    1.11
     estar
    1.10
    POSITIVE LOGITS
    ا
    1.89
     وفي
    1.72
    ı
    1.39
     kojem
    1.36
    부터
    1.35
    ü
    1.35
    quir
    1.27
    い
    1.27
     وبين
    1.25
    ılarak
    1.24
    Act Density 0.173%

    No Known Activations