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

    Neuronpedia

    INDEX
    Explanations

    0 or 5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    會議
    -0.07
    셤
    -0.07
     impe
    -0.07
    专栏
    -0.07
    痦
    -0.07
    煅
    -0.06
    债
    -0.06
    עבר
    -0.06
    单项
    -0.06
    褪
    -0.06
    POSITIVE LOGITS
    .</
    0.08
     str
    0.08
    _connection
    0.07
     gri
    0.07
    之地
    0.07
    .",↵
    0.07
     uncle
    0.07
     Honor
    0.07
     shadow
    0.07
    ،
    0.07
    Act Density 0.059%

    No Known Activations