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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utsch
    -0.07
    不可
    -0.06
     STAR
    -0.06
    opl
    -0.06
    动生成
    -0.06
     Brook
    -0.06
     bulunur
    -0.06
     Minnesota
    -0.06
     Ric
    -0.05
    нен
    -0.05
    POSITIVE LOGITS
     liaison
    0.07
     ＿
    0.07
    notations
    0.07
    ventas
    0.06
    IH
    0.06
    .Tree
    0.06
     vd
    0.06
     інт
    0.06
     reliance
    0.06
     nghiêm
    0.06
    Act Density 0.015%

    No Known Activations