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

    Neuronpedia

    INDEX
    Explanations

    explaining complex concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     التي
    0.44
     of
    0.42
     제가
    0.39
     आफ
    0.36
     của
    0.36
     เชื่อ
    0.35
     that
    0.35
     Держа
    0.35
    ของการ
    0.34
     của
    0.33
    POSITIVE LOGITS
    重要な
    0.37
     realistic
    0.36
    非常に
    0.34
     misguided
    0.32
    ত্রিম
    0.31
     impromptu
    0.31
     wichtige
    0.31
    ographiques
    0.31
     disastrous
    0.30
     tecnológico
    0.30
    Act Density 0.161%

    No Known Activations