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

    Neuronpedia

    INDEX
    Explanations

    programming paradigms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ֩
    0.49
     विभागीय
    0.48
    olojik
    0.46
    olutamente
    0.45
    incerely
    0.44
    ֜
    0.44
    ﮟ
    0.44
    etically
    0.43
    rically
    0.43
    })}{
    0.42
    POSITIVE LOGITS
    ങ്ങളാണ്
    0.50
    I
    0.48
    aries
    0.47
    manship
    0.47
    m
    0.46
    OS
    0.46
     I
    0.46
    ları
    0.46
    烃
    0.46
    وں
    0.45
    Act Density 0.015%

    No Known Activations