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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bow
    -0.07
    下面是小
    -0.07
     Horror
    -0.07
     Bá
    -0.07
    opor
    -0.07
    是最
    -0.07
    陈列
    -0.07
    戛
    -0.07
    �
    -0.07
     Moo
    -0.07
    POSITIVE LOGITS
     datum
    0.07
    确定
    0.07
    �
    0.07
    >`
    0.07
    졍
    0.07
     UAV
    0.07
    远离
    0.07
    endencies
    0.07
    晅
    0.07
    /day
    0.06
    Act Density 0.011%

    No Known Activations