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

    Neuronpedia

    INDEX
    Explanations

    level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ตนเอง
    -0.07
     gentlemen
    -0.07
    jr
    -0.07
     mang
    -0.07
    bands
    -0.07
     sint
    -0.07
     chests
    -0.06
    行政处罚
    -0.06
    m
    -0.06
    t
    -0.06
    POSITIVE LOGITS
    퀄
    0.08
    ubah
    0.07
     совет
    0.07
    ,Q
    0.07
    ぐらい
    0.07
    ouver
    0.07
    KH
    0.07
     Westminster
    0.07
    UB
    0.07
    .Global
    0.07
    Act Density 0.001%

    No Known Activations