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

    Neuronpedia

    INDEX
    Explanations

    clear or errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    appear
    0.41
    appears
    0.40
    abah
    0.39
    ♬
    0.39
    ákat
    0.39
    }{
    0.38
    व्य
    0.38
    !');
    0.38
    ígenes
    0.38
    ah
    0.37
    POSITIVE LOGITS
     учун
    0.47
     ثقاف
    0.46
     Telugu
    0.45
     beruf
    0.44
     داعش
    0.44
     classpath
    0.43
     Marketing
    0.43
     เพื่อ
    0.43
     Marathi
    0.43
    ל
    0.43
    Act Density 0.006%

    No Known Activations