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

    Neuronpedia

    INDEX
    Explanations

    introducing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     minors
    0.48
    褻
    0.48
     exhibitors
    0.42
    クール
    0.42
     வலி
    0.42
     imput
    0.42
     allegations
    0.41
     ส
    0.41
    平时
    0.41
    ūs
    0.41
    POSITIVE LOGITS
     cinq
    0.53
     buck
    0.50
    K
    0.50
    appliquer
    0.49
     cinque
    0.49
    H
    0.48
     haya
    0.48
     svij
    0.48
    r
    0.46
    idf
    0.45
    Act Density 0.000%

    No Known Activations