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

    Neuronpedia

    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.08
     driving
    -0.08
     welfare
    -0.08
     whistle
    -0.08
     leader
    -0.08
     Welfare
    -0.07
    SPI
    -0.07
     Pau
    -0.07
    会员
    -0.07
    禁
    -0.07
    POSITIVE LOGITS
     cad
    0.08
    dfs
    0.08
    iot
    0.08
     hend
    0.07
    ENTITY
    0.07
    ાઓ
    0.07
     Derm
    0.07
    های
    0.07
    empot
    0.07
     পালন
    0.07
    Act Density 0.011%

    No Known Activations