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

    Neuronpedia

    INDEX
    Explanations

    scientific or mathematical terminology in a document

    oai_token-act-pair · gemini-2.0-flash

    scientific, mathematical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.59
     Preheat
    -0.58
     quench
    -0.57
     Athene
    -0.56
     getResources
    -0.56
    ductory
    -0.54
     Maharaja
    -0.54
     Schengen
    -0.54
     Eta
    -0.54
    CrossRef
    -0.54
    POSITIVE LOGITS
     direction
    0.96
     Direction
    0.78
    Direction
    0.75
    direction
    0.69
     richting
    0.68
     directions
    0.66
     arah
    0.65
     DIRECTION
    0.61
     direzione
    0.60
    ایج
    0.59
    Act Density 3.294%

    No Known Activations