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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yoluyla
    -0.07
    ratio
    -0.06
    ugu
    -0.06
     cycle
    -0.06
     loaf
    -0.06
    цию
    -0.06
     pero
    -0.06
     periods
    -0.06
     jclass
    -0.06
    [z
    -0.06
    POSITIVE LOGITS
    formatted
    0.07
     formatted
    0.07
    =forms
    0.07
    _busy
    0.07
    .setString
    0.07
    FORMAT
    0.07
     misinformation
    0.07
     Formatter
    0.06
     Gust
    0.06
    .fm
    0.06
    Act Density 0.011%

    No Known Activations