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

    Neuronpedia

    INDEX
    Explanations

    worship

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cookies
    -0.08
     noises
    -0.07
     sunscreen
    -0.07
     зад
    -0.07
    猴子
    -0.07
    -stage
    -0.07
    还挺
    -0.07
    aze
    -0.07
     pill
    -0.07
     btn
    -0.07
    POSITIVE LOGITS
    (contract
    0.07
     sigma
    0.07
    W
    0.07
    .selectAll
    0.07
     confessed
    0.07
    深度融合
    0.06
    DefaultValue
    0.06
    лим
    0.06
    𝙬
    0.06
     diplomat
    0.06
    Act Density 0.005%

    No Known Activations