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

    Neuronpedia

    INDEX
    Explanations

    public services and spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.80
     كتاب
    0.64
     İyi
    0.59
     будут
    0.59
    كا
    0.58
    在
    0.57
    كتب
    0.56
    .
    0.56
     в
    0.55
     größ
    0.54
    POSITIVE LOGITS
    ہ
    0.75
    ad
    0.66
     public
    0.66
    یی
    0.66
    지
    0.61
    ן
    0.59
    t
    0.58
     خمسه
    0.57
    um
    0.53
    out
    0.52
    Act Density 0.051%

    No Known Activations