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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and results in equations

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

    get/obtain result followed by formula/math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Taktlose
    -0.70
    EDEFAULT
    -0.68
     незавершена
    -0.63
     Normdatei
    -0.62
     AspNetCore
    -0.60
    DeleteBehavior
    -0.58
    WriteTagHelper
    -0.57
    Tembelea
    -0.56
     تضيفلها
    -0.56
    ParseTree
    -0.54
    POSITIVE LOGITS
     dalamnya
    0.37
    ępnie
    0.35
    SharedCtor
    0.35
     księ
    0.35
     urbanos
    0.33
     zufolge
    0.33
    setVerticalGroup
    0.33
     leggen
    0.33
     ortaya
    0.32
     krijg
    0.32
    Act Density 0.138%

    No Known Activations