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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    去找
    -0.07
    adem
    -0.07
    Gay
    -0.07
    帐
    -0.07
    藤
    -0.06
     Mad
    -0.06
    𝖔
    -0.06
    productId
    -0.06
    Mon
    -0.06
    POSITIVE LOGITS
    =n
    0.08
    IVAL
    0.07
    🍕
    0.07
    ✣
    0.07
    南沙
    0.07
    ,string
    0.07
    _Final
    0.07
    🔎
    0.07
    activation
    0.07
     unde
    0.07
    Act Density 0.025%

    No Known Activations