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

    Neuronpedia

    INDEX
    Explanations

    Positive sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ancers
    -0.06
     contamination
    -0.06
    трон
    -0.06
     anew
    -0.06
    ВО
    -0.06
    ≦
    -0.06
    izational
    -0.06
     Preserve
    -0.06
    _sz
    -0.06
     obligations
    -0.06
    POSITIVE LOGITS
    ------------------------------------------------------------------------------------------------
    0.07
     Kathleen
    0.07
    .RegisterType
    0.06
    蛇
    0.06
     바라
    0.06
     ------------------------------------------------------------------------------------------------
    0.06
    0.06
    ocese
    0.06
     ­
    0.06
    DefaultCellStyle
    0.06
    Act Density 0.168%

    No Known Activations