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

    Neuronpedia

    INDEX
    Explanations

    female

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trả
    -0.07
     JSName
    -0.07
     weeds
    -0.06
     Пар
    -0.06
    <LM
    -0.06
     Pis
    -0.06
     מצ
    -0.06
     firstName
    -0.06
    ANTE
    -0.06
    实践经验
    -0.06
    POSITIVE LOGITS
     Western
    0.07
    `,
    0.07
    ℧
    0.07
    	Key
    0.07
    ”，
    0.07
    	format
    0.06
     obvious
    0.06
    中药
    0.06
    /column
    0.06
    puted
    0.06
    Act Density 0.030%

    No Known Activations