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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or symbols often associated with variables or expressions in mathematical contexts

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

    Letters within math expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.43
     referrerpolicy
    -0.40
    centralwidget
    -0.38
    Välislingid
    -0.36
    gone
    -0.36
     näin
    -0.36
    Personensuche
    -0.35
    IsContent
    -0.35
    Autoritní
    -0.35
    MigrationBuilder
    -0.35
    POSITIVE LOGITS
    intios
    0.56
    ̈́
    0.48
    Демографія
    0.47
    Ecotoxicity
    0.47
    جوايز
    0.47
     Walkover
    0.46
     Chwiliwch
    0.45
    :✨
    0.45
     itemName
    0.44
     pán
    0.44
    Act Density 0.675%

    No Known Activations