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

    Neuronpedia

    INDEX
    Explanations

    62

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dir
    0.45
     amends
    0.42
    ded
    0.41
    da
    0.41
    ものが
    0.41
    िक्रमा
    0.40
     torno
    0.39
    ਰ
    0.39
    lk
    0.39
    ठे
    0.39
    POSITIVE LOGITS
    мо
    0.39
    वंत
    0.38
    大量
    0.38
    र्मेंद्र
    0.38
     amply
    0.38
    Needless
    0.36
     categorically
    0.36
     কারা
    0.36
    祓
    0.35
    פים
    0.35
    Act Density 0.008%

    No Known Activations