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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MIC
    -0.07
     Knee
    -0.07
    .SM
    -0.07
     ENG
    -0.07
     Legislature
    -0.07
    一句
    -0.07
    风电
    -0.07
     UNIQUE
    -0.07
    orum
    -0.07
    几句
    -0.07
    POSITIVE LOGITS
    广告服务
    0.08
    образ
    0.07
    作り
    0.07
     deix
    0.07
    幪
    0.07
     реш
    0.07
    埕
    0.07
     hesabı
    0.07
     постоян
    0.06
    決定
    0.06
    Act Density 0.005%

    No Known Activations