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

    Neuronpedia

    INDEX
    Explanations

    fonts, scrollbars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    coe
    -0.06
    /build
    -0.06
    컴
    -0.06
    voř
    -0.06
    $b
    -0.06
    aad
    -0.06
    广
    -0.05
    (cards
    -0.05
    HU
    -0.05
     fingertips
    -0.05
    POSITIVE LOGITS
    ประ
    0.07
     InputStream
    0.07
    пов
    0.07
     POD
    0.07
    ../
    0.07
    _OPTIONS
    0.06
     назад
    0.06
    া�
    0.06
     грун
    0.06
    ลล
    0.06
    Act Density 0.002%

    No Known Activations