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

    Neuronpedia

    INDEX
    Explanations

    focus on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.42
    ی
    0.40
     [
    0.39
    Fees
    0.39
     ,
    0.38
    Fiction
    0.38
     fake
    0.38
     fiction
    0.38
     in
    0.37
     儿童
    0.37
    POSITIVE LOGITS
    טו
    0.46
    טה
    0.43
    Según
    0.42
    ტერ
    0.42
    ತಾ
    0.41
    жели
    0.41
     Según
    0.40
    ಾರ್ಟ
    0.40
    ಕ್ಸ್
    0.40
     Toul
    0.40
    Act Density 0.004%

    No Known Activations