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

    Neuronpedia

    INDEX
    Explanations

    denominator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     využití
    -0.08
     clay
    -0.07
     LN
    -0.07
     parçası
    -0.07
     سابق
    -0.06
     roller
    -0.06
     Railway
    -0.06
    歲
    -0.06
     gord
    -0.06
    moon
    -0.06
    POSITIVE LOGITS
     purported
    0.06
     measured
    0.06
     Contrib
    0.06
     Jenna
    0.06
    _infos
    0.06
    stdexcept
    0.06
    (B
    0.06
    jest
    0.06
    。これ
    0.06
    _period
    0.06
    Act Density 0.001%

    No Known Activations