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

    Neuronpedia

    INDEX
    Explanations

    numerical values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.45
    ↵
    0.41
    م
    0.41
    in
    0.40
    ก
    0.39
    p
    0.38
    ే
    0.38
    ంట్
    0.36
     ਉ
    0.36
    ব
    0.35
    POSITIVE LOGITS
    .
    0.67
    0.54
    이다
    0.45
    ется
    0.45
    arı
    0.41
    \
    0.40
    ,.
    0.40
    아요
    0.39
    .`
    0.39
    하이
    0.38
    Act Density 0.370%

    No Known Activations