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

    Neuronpedia

    INDEX
    Explanations

    html title tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     powder
    0.51
     on
    0.49
     high
    0.49
     councils
    0.49
     was
    0.49
     is
    0.49
    5
    0.47
     Powder
    0.46
     af
    0.46
     ay
    0.46
    POSITIVE LOGITS
    ನ್
    0.45
     ملازمت
    0.45
    Ejercicio
    0.42
     واکنش
    0.42
    Ⲣ
    0.41
     gacche
    0.41
     божомолдору
    0.40
     رشته
    0.40
    ِن
    0.40
    ליה
    0.40
    Act Density 0.004%

    No Known Activations