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

    Neuronpedia

    INDEX
    Explanations

    Formal communications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    冶炼
    -0.07
     отдых
    -0.07
    发表了
    -0.07
     inventor
    -0.07
     Hos
    -0.07
    청소
    -0.07
    공
    -0.07
    滋
    -0.07
     printk
    -0.06
    统统
    -0.06
    POSITIVE LOGITS
    	ON
    0.08
    驵
    0.08
    cite
    0.07
    fbe
    0.07
    훑
    0.07
     paddle
    0.07
    _JOIN
    0.07
    ąż
    0.07
    saldo
    0.07
    SAME
    0.07
    Act Density 0.468%

    No Known Activations