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

    Neuronpedia

    INDEX
    Explanations

    f1 score

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bing
    -0.06
    !(
    -0.06
    cams
    -0.06
     gode
    -0.06
    .course
    -0.06
    .sales
    -0.06
    stories
    -0.06
     appreciate
    -0.06
     использ
    -0.06
     улуч
    -0.06
    POSITIVE LOGITS
    Vý
    0.07
     Afghanistan
    0.07
     sg
    0.06
     penal
    0.06
    /****************
    0.06
    ект
    0.06
    Vous
    0.06
     newPassword
    0.06
     "";↵↵
    0.06
     sout
    0.06
    Act Density 0.001%

    No Known Activations