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

    Neuronpedia

    INDEX
    Explanations

    Code and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cli
    -0.08
     finals
    -0.08
    榜样
    -0.07
     surtout
    -0.07
    ᗗ
    -0.07
    Relative
    -0.07
     flush
    -0.07
    杷
    -0.07
    �
    -0.07
    机体
    -0.07
    POSITIVE LOGITS
     entering
    0.07
    есть
    0.07
    /Input
    0.07
     sheet
    0.07
    .removeEventListener
    0.07
    东方财富
    0.07
    욬
    0.07
     PAY
    0.07
    拖欠
    0.06
    传
    0.06
    Act Density 0.009%

    No Known Activations