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

    Neuronpedia

    INDEX
    Explanations

    interview excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mae
    -0.06
     BCM
    -0.06
    _SET
    -0.06
    .writerow
    -0.06
     nums
    -0.06
     yabancı
    -0.06
     nguy
    -0.06
     输入
    -0.06
    Oak
    -0.06
    /db
    -0.06
    POSITIVE LOGITS
    izzy
    0.07
    下载
    0.06
    bird
    0.06
    666
    0.06
    650
    0.06
     внимание
    0.06
    inces
    0.06
    ъ
    0.06
    بد
    0.06
     Jer
    0.06
    Act Density 0.122%

    No Known Activations