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

    Neuronpedia

    INDEX
    Explanations

    Dec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    全省
    -0.08
    .contrib
    -0.07
    compute
    -0.07
    )"↵
    -0.07
    есь
    -0.06
    婞
    -0.06
     개인정보
    -0.06
     repreh
    -0.06
    :f
    -0.06
    _smart
    -0.06
    POSITIVE LOGITS
    ков
    0.07
    ADING
    0.07
    Tool
    0.07
    法律顾问
    0.07
    욺
    0.07
     slap
    0.06
    隍
    0.06
    ferences
    0.06
    林
    0.06
    wang
    0.06
    Act Density 0.001%

    No Known Activations