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

    Neuronpedia

    INDEX
    Explanations

    numerical variables and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Russo
    0.42
    覧
    0.41
     Elkus
    0.39
     گروه
    0.38
     serata
    0.38
    bey
    0.38
     druż
    0.38
    ულია
    0.38
     directo
    0.37
    VG
    0.37
    POSITIVE LOGITS
    变量
    0.53
    NSInteger
    0.53
    Integer
    0.53
    randomNumber
    0.52
     integer
    0.50
    ifelse
    0.50
    num
    0.49
     variabile
    0.49
     integers
    0.47
    整数
    0.47
    Act Density 0.117%

    No Known Activations