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

    Neuronpedia

    INDEX
    Explanations

    left

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chemy
    -0.07
    晨
    -0.07
    adier
    -0.07
     times
    -0.07
    迟
    -0.07
    土耳
    -0.07
    ﾞ
    -0.07
    _ctl
    -0.06
    中毒
    -0.06
    ifying
    -0.06
    POSITIVE LOGITS
    访谈
    0.07
    总承包
    0.07
    吊顶
    0.07
    岭南
    0.07
     качество
    0.07
    (latitude
    0.07
    唬
    0.07
    .SetValue
    0.07
     גיל
    0.07
     philosophical
    0.07
    Act Density 0.009%

    No Known Activations