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

    Neuronpedia

    INDEX
    Explanations

    says

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    元件
    -0.07
    ➲
    -0.07
     actionTypes
    -0.07
    .Help
    -0.06
     ADDR
    -0.06
     Clears
    -0.06
    .getAs
    -0.06
    供应链
    -0.06
    .handleClick
    -0.06
    ]},
    -0.06
    POSITIVE LOGITS
    耶穌
    0.07
     trì
    0.07
     Battles
    0.07
    ющие
    0.07
     medical
    0.07
    odash
    0.07
     genetic
    0.06
     pudding
    0.06
    da
    0.06
    erals
    0.06
    Act Density 0.091%

    No Known Activations