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

    Neuronpedia

    INDEX
    Explanations

    dots and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hitam
    0.43
     insanely
    0.39
     හෝ
    0.38
     അടു
    0.37
    ဆင့်
    0.37
    andingan
    0.36
    ⇵
    0.36
    /#{
    0.36
     می‌تواند
    0.35
     KW
    0.35
    POSITIVE LOGITS
    ~.,
    0.55
    ··
    0.47
    ····
    0.45
    -,
    0.44
    ·
    0.42
    -.
    0.41
    ;,
    0.41
    婦
    0.41
     ..,
    0.41
    μαι
    0.40
    Act Density 0.004%

    No Known Activations