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

    Neuronpedia

    INDEX
    Explanations

    on behalf of, on average, on occasion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exchanged
    0.46
     unseren
    0.45
     exchange
    0.44
     unserem
    0.44
     COMPENSATION
    0.44
     depreci
    0.41
     hypothesis
    0.41
     transfers
    0.41
     ihren
    0.41
     danych
    0.41
    POSITIVE LOGITS
    ıldığı
    0.49
    ceği
    0.43
    bonne
    0.42
    Ngày
    0.42
    看待
    0.41
    Minist
    0.41
    iosas
    0.41
    aday
    0.40
    day
    0.40
     Khánh
    0.40
    Act Density 0.018%

    No Known Activations