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

    Neuronpedia

    INDEX
    Explanations

    dualism and switching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.65
    ad
    0.57
    ز
    0.55
    ಹಾಸ
    0.53
    ة
    0.53
    jest
    0.50
     ティ
    0.50
     Girl
    0.49
     t
    0.49
     Το
    0.48
    POSITIVE LOGITS
     cityName
    0.49
    finalize
    0.44
    도록
    0.44
     bland
    0.43
    õi
    0.42
    nextLine
    0.42
    textured
    0.41
     डिपार्टमेंट
    0.41
    iformes
    0.41
    gameOver
    0.40
    Act Density 0.002%

    No Known Activations