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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theat
    -0.07
     Estr
    -0.07
     haus
    -0.06
    Hum
    -0.06
    师
    -0.06
     cultivated
    -0.06
     баж
    -0.06
     hatred
    -0.06
    Runs
    -0.06
    _indent
    -0.06
    POSITIVE LOGITS
    .urls
    0.07
     $_
    0.07
    aincontri
    0.07
    ?";↵
    0.07
    ";
    0.07
    <span
    0.06
     OpenGL
    0.06
    $info
    0.06
    ницы
    0.06
     */↵↵↵↵
    0.06
    Act Density 0.016%

    No Known Activations