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

    Neuronpedia

    INDEX
    Explanations

    names, etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contours
    0.48
     outlay
    0.45
     Receivable
    0.45
     prospectus
    0.44
     contour
    0.43
     combustibles
    0.42
     cholester
    0.41
     configure
    0.39
     gamut
    0.39
     configurable
    0.39
    POSITIVE LOGITS
     Michael
    0.97
     Steve
    0.97
     David
    0.95
     Richard
    0.93
     Mike
    0.93
     Chris
    0.93
     Kevin
    0.92
     Peter
    0.91
     Tony
    0.91
     Stephen
    0.90
    Act Density 0.006%

    No Known Activations