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

    Neuronpedia

    INDEX
    Explanations

    Boundaries and limits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gway
    -1.02
    anova
    -0.72
    owan
    -0.70
     area
    -0.63
     focus
    -0.60
    kai
    -0.59
     focusing
    -0.55
     مشين
    -0.55
     kasarigan
    -0.54
    jected
    -0.52
    POSITIVE LOGITS
    WriteLiteral
    0.63
    ForRow
    0.58
     unknownFields
    0.58
    wright
    0.56
    magin
    0.55
    fficient
    0.54
    HasAnnotation
    0.54
     nepo
    0.52
     näm
    0.52
    ANZA
    0.52
    Act Density 0.429%

    No Known Activations