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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ):
    -0.07
     Birch
    -0.07
    aim
    -0.07
    😝
    -0.07
    -contrib
    -0.06
    あな
    -0.06
    变更
    -0.06
     Gazette
    -0.06
     caz
    -0.06
     BANK
    -0.06
    POSITIVE LOGITS
    干事创业
    0.07
    海淀
    0.07
     ng
    0.07
    峡谷
    0.07
    同
    0.07
    體驗
    0.07
    aging
    0.07
    🅶
    0.07
    矢
    0.07
    Development
    0.06
    Act Density 0.011%

    No Known Activations