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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ホーム
    -0.08
    怎么看
    -0.07
    铪
    -0.06
     demean
    -0.06
     harness
    -0.06
    -domain
    -0.06
    老龄化
    -0.06
     misdemean
    -0.06
     setBackgroundImage
    -0.06
     Coupe
    -0.06
    POSITIVE LOGITS
    标题
    0.08
    ycle
    0.08
    _SECTION
    0.07
    ݴ
    0.07
     ');↵
    0.07
    _regular
    0.07
    ecure
    0.07
    cat
    0.06
    风吹
    0.06
    一块
    0.06
    Act Density 0.157%

    No Known Activations