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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sign
    -0.08
    不利
    -0.08
    uint
    -0.07
     flush
    -0.07
    gard
    -0.07
    flutter
    -0.07
    disc
    -0.07
     USER
    -0.07
    linger
    -0.07
    int
    -0.06
    POSITIVE LOGITS
     والع
    0.07
    paired
    0.06
    ispiel
    0.06
    致电
    0.06
    	O
    0.06
    交易所
    0.06
    xAE
    0.06
     `[
    0.06
    _Remove
    0.06
    ymce
    0.06
    Act Density 0.003%

    No Known Activations