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

    Neuronpedia

    INDEX
    Explanations

    star patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Matches
    0.46
    Ⲑ
    0.44
    Dictionaries
    0.43
    ллі
    0.43
    붐
    0.43
     ორგანო
    0.42
     літера
    0.39
     comod
    0.39
    加速度
    0.39
    ʣ
    0.38
    POSITIVE LOGITS
     January
    0.47
    uran
    0.46
     SL
    0.42
    inan
    0.41
    esk
    0.39
    osine
    0.38
     Ne
    0.38
    وزه
    0.38
     Ian
    0.37
     vacated
    0.37
    Act Density 0.000%

    No Known Activations