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

    Neuronpedia

    INDEX
    Explanations

    technical discussions and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.60
     penalty
    0.54
     timer
    0.48
    payment
    0.47
     system
    0.47
     chemicals
    0.47
     시간
    0.46
    d
    0.46
     활
    0.46
     blooming
    0.45
    POSITIVE LOGITS
    ت
    0.48
    нија
    0.45
    ۴
    0.43
    حسن
    0.43
     proz
    0.43
    社會
    0.43
    叅
    0.42
    ح
    0.41
    二是
    0.41
     Tentang
    0.40
    Act Density 0.000%

    No Known Activations