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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Teen
    -0.07
    套房
    -0.07
    快餐
    -0.07
    -Pro
    -0.07
     casinos
    -0.07
     آ
    -0.07
     Emin
    -0.06
     devoid
    -0.06
    دين
    -0.06
    ás
    -0.06
    POSITIVE LOGITS
    _IF
    0.07
    就把
    0.07
    	initial
    0.07
    .trigger
    0.06
     committed
    0.06
    עשר
    0.06
     partition
    0.06
    长效
    0.06
     :";↵
    0.06
    reak
    0.06
    Act Density 0.002%

    No Known Activations