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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical analysis and definitions of functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorTagHelper
    -0.36
    Literatuur
    -0.35
     uusi
    -0.32
     utafitiHapana
    -0.32
    Карьера
    -0.32
     emisiones
    -0.32
    μως
    -0.31
     juego
    -0.30
     réun
    -0.30
    ionato
    -0.30
    POSITIVE LOGITS
     point
    1.73
    point
    1.55
     points
    1.55
     Point
    1.54
     POINT
    1.52
    Point
    1.43
    points
    1.41
     Points
    1.39
     POINTS
    1.38
    POINT
    1.36
    Act Density 0.093%

    No Known Activations