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

    Neuronpedia

    INDEX
    Explanations

    Math notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handler
    -0.07
    vided
    -0.07
     cabins
    -0.06
    <|begin_of_text|>
    -0.06
    .SIG
    -0.06
    -ar
    -0.06
     decks
    -0.06
    Someone
    -0.06
    лих
    -0.06
    MESS
    -0.06
    POSITIVE LOGITS
     dalla
    0.07
     Broncos
    0.06
    baar
    0.06
     Зем
    0.06
    alış
    0.06
    下载次数
    0.06
    .flink
    0.06
    _"
    0.06
    prototype
    0.06
     допомоги
    0.06
    Act Density 0.048%

    No Known Activations