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

    Neuronpedia

    INDEX
    Explanations

    institutional affiliation or department names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     त्यो
    0.73
    ં
    0.73
    वणे
    0.70
    imwrite
    0.69
     мере
    0.65
    ভি
    0.65
     मेल
    0.64
     рай
    0.63
     arada
    0.63
    ल्
    0.62
    POSITIVE LOGITS
     of
    1.75
     ऑफ
    1.54
     ఆఫ్
    1.45
     Of
    1.39
    of
    1.30
     ഓഫ്
    1.28
     Against
    1.21
     for
    1.21
     Concerning
    1.20
     آف
    1.18
    Act Density 0.159%

    No Known Activations