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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gins
    -0.06
    [-
    -0.06
    ामग
    -0.06
     glyc
    -0.06
    싸
    -0.06
    яют
    -0.06
     outra
    -0.06
     comparable
    -0.06
    focused
    -0.06
     başka
    -0.06
    POSITIVE LOGITS
    .hasMore
    0.07
     outs
    0.07
    .assert
    0.07
    중에
    0.07
     Holy
    0.07
    ائرة
    0.06
     seç
    0.06
    .ReadLine
    0.06
     Männer
    0.06
     uploads
    0.06
    Act Density 0.217%

    No Known Activations