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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ırlar
    -0.07
    -store
    -0.07
     jak
    -0.07
    apk
    -0.07
     Mavericks
    -0.07
     CST
    -0.07
    larınızı
    -0.07
    Fast
    -0.06
     ry
    -0.06
     increases
    -0.06
    POSITIVE LOGITS
    of
    0.08
     Of
    0.08
    Of
    0.07
     웃
    0.07
    のお
    0.07
    教
    0.07
    (off
    0.07
     мяс
    0.07
    OF
    0.07
    の子
    0.07
    Act Density 0.022%

    No Known Activations