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

    Neuronpedia

    INDEX
    Explanations

    (s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Index
    -0.07
    🍅
    -0.07
    勉
    -0.07
    瘾
    -0.06
     excerpts
    -0.06
    ')}}</
    -0.06
    ']))
↵
    -0.06
    告訴
    -0.06
    סרט
    -0.06
    而是
    -0.06
    POSITIVE LOGITS
    系列产品
    0.08
     leftovers
    0.07
    ização
    0.07
    ografia
    0.06
    本文
    0.06
    isé
    0.06
    _Handle
    0.06
    .Remove
    0.06
     الرحمن
    0.06
    imenti
    0.06
    Act Density 0.002%

    No Known Activations