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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JL
    -0.07
     номер
    -0.07
    Dot
    -0.07
    发改
    -0.07
    至
    -0.07
    注明出处
    -0.06
    func
    -0.06
    🅱
    -0.06
    涌现出
    -0.06
     Paging
    -0.06
    POSITIVE LOGITS
     Austria
    0.07
     CHILD
    0.07
     bounded
    0.07
     aggression
    0.07
    !("
    0.06
    生物质
    0.06
     Friendly
    0.06
    拍照
    0.06
    杀人
    0.06
    ottes
    0.06
    Act Density 0.137%

    No Known Activations