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

    Neuronpedia

    INDEX
    Explanations

    giving advice or support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guidance
    -0.88
     advice
    -0.86
     aspects
    -0.80
     corner
    -0.80
    aspects
    -0.76
    advice
    -0.75
     corners
    -0.74
     oversight
    -0.71
    guidance
    -0.71
     Advice
    -0.69
    POSITIVE LOGITS
     EconPapers
    0.98
     of
    0.76
     kasarigan
    0.66
    ValueStyle
    0.62
     calendriers
    0.61
     שוליים
    0.56
     BoxDecoration
    0.53
     חיצוניים
    0.53
    printStackTrace
    0.52
    HandlerContext
    0.52
    Act Density 0.037%

    No Known Activations