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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    送
    -0.07
     quer
    -0.07
     tiếp
    -0.07
    отор
    -0.07
    thinking
    -0.06
     cult
    -0.06
    controller
    -0.06
    跳
    -0.06
     باش
    -0.06
    ulatory
    -0.06
    POSITIVE LOGITS
    -md
    0.07
     Đảng
    0.06
    ライト
    0.06
     IReadOnly
    0.06
     Accessibility
    0.06
    fel
    0.06
    lenen
    0.06
    _detail
    0.05
     Void
    0.05
    isOk
    0.05
    Act Density 0.005%

    No Known Activations