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

    Neuronpedia

    INDEX
    Explanations

    variable names and mathematical expressions

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

    Mathematical or chemical formulas

    np_acts-logits-general · gemini-2.0-flash

    mathematical, code or legal expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.48
     […]
    -0.42
     kohdetta
    -0.41
    rungsseite
    -0.40
    astéroïdes
    -0.40
     Италијани
    -0.38
    Setiap
    -0.37
     EconPapers
    -0.37
    BitConverter
    -0.35
    firmasi
    -0.34
    POSITIVE LOGITS
     ویکی‌پدیا
    0.64
     للاسماء
    0.60
    Portály
    0.57
    Geplaatst
    0.52
     useAppContext
    0.52
    دانشنامهٔ
    0.51
    évaluateur
    0.50
    ConstraintMaker
    0.49
    ViewImports
    0.48
    LabelTagHelper
    0.47
    Act Density 0.908%

    No Known Activations