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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .registration
    -0.07
    Destroy
    -0.07
    _hard
    -0.07
     paid
    -0.06
    /help
    -0.06
     mural
    -0.06
     promoter
    -0.06
     Directive
    -0.06
     Supplements
    -0.06
    _Box
    -0.06
    POSITIVE LOGITS
    										↵
    0.07
     QHBoxLayout
    0.07
     '))↵
    0.06
    stoup
    0.06
    �
    0.06
    InnerHTML
    0.06
    �行
    0.06
     kleinen
    0.06
    ){
↵
↵
    0.06
    .setViewport
    0.06
    Act Density 0.007%

    No Known Activations