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

    Neuronpedia

    INDEX
    Explanations

    military related texts and texts giving lots of measurements

    oai_token-act-pair · gemini-2.0-flash

    measure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eventdata
    -0.79
    UrlResolution
    -0.73
     nahilalakip
    -0.72
    fromnode
    -0.70
    IContainer
    -0.64
     IndexPath
    -0.60
    <%=
    -0.59
    tagHelperRunner
    -0.59
     StatelessWidget
    -0.58
    Xna
    -0.58
    POSITIVE LOGITS
     level
    0.91
    level
    0.81
     LEVEL
    0.76
     Level
    0.75
    Level
    0.73
     levels
    0.70
    LEVEL
    0.69
     nivel
    0.68
     measure
    0.67
     niveau
    0.65
    Act Density 1.208%

    No Known Activations