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

    Neuronpedia

    INDEX
    Explanations

    scientific comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    咨询
    -0.07
    MJ
    -0.07
    '=>['
    -0.06
     Mill
    -0.06
    �
    -0.06
    _PAUSE
    -0.06
    .custom
    -0.06
     ﺍ
    -0.06
    postData
    -0.06
    ΗΝ
    -0.06
    POSITIVE LOGITS
     setMessage
    0.07
     жовтня
    0.07
     indian
    0.07
    .Debugf
    0.06
                         ↵
    0.06
     civilians
    0.06
                           ↵
    0.06
    ↵    ↵    ↵
    0.06
    َن
    0.06
    icus
    0.06
    Act Density 0.050%

    No Known Activations