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

    Neuronpedia

    INDEX
    Explanations

    correctly setting similarity encounter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    神经网络
    0.41
     schwar
    0.41
     tohoto
    0.40
     گاز
    0.40
     Här
    0.38
     dalších
    0.38
    ressed
    0.38
     ماشینونه
    0.37
     الذين
    0.37
     produits
    0.37
    POSITIVE LOGITS
     exists
    0.45
     status
    0.42
     नहीं
    0.41
     complexion
    0.41
     наличии
    0.41
     phenomenon
    0.41
     continuum
    0.41
     courtship
    0.40
    पर्य
    0.39
     congruent
    0.39
    Act Density 0.008%

    No Known Activations