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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clothing
    -0.06
    _enc
    -0.06
     maximum
    -0.06
     denn
    -0.06
    /dc
    -0.06
    isible
    -0.06
     Convert
    -0.06
     conducts
    -0.06
    办法
    -0.06
    高达
    -0.06
    POSITIVE LOGITS
    .REG
    0.08
    钢厂
    0.07
    tweet
    0.07
    趋于
    0.07
     getItemCount
    0.07
     freel
    0.07
    �
    0.07
    Ầ
    0.06
    泔
    0.06
    laus
    0.06
    Act Density 0.012%

    No Known Activations