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

    Neuronpedia

    INDEX
    Explanations

    code structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ennzeichnet
    0.49
     to
    0.45
    ফটেন্যান্ট
    0.43
    ెస్
    0.42
    ítico
    0.42
     فيلم
    0.42
    ités
    0.41
    𝘰
    0.41
    igating
    0.41
    {//
    0.41
    POSITIVE LOGITS
    z
    0.73
    c
    0.58
    x
    0.57
    g
    0.56
    ↵
    0.56
    q
    0.54
    ле
    0.51
    ى
    0.48
    u
    0.47
    k
    0.46
    Act Density 0.400%

    No Known Activations