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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gender
    -0.07
    fre
    -0.07
    乡村
    -0.07
     pension
    -0.07
     command
    -0.07
    督促
    -0.06
     Apollo
    -0.06
    뇗
    -0.06
    案件
    -0.06
    聘请
    -0.06
    POSITIVE LOGITS
     Publications
    0.07
    前述
    0.07
    planation
    0.07
     Experience
    0.07
     Kath
    0.07
     Photos
    0.07
    猫
    0.07
    	Description
    0.07
     PlayStation
    0.07
     Castillo
    0.07
    Act Density 0.000%

    No Known Activations