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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and expressions related to equations

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

    function definition `u(...)` or variable `u =`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endcsname
    -0.64
    CloseOperation
    -0.58
     AspNetCore
    -0.58
     defaultstate
    -0.58
     snippetHide
    -0.55
    FieldOffsetTable
    -0.53
     ModelExpression
    -0.50
    PYX
    -0.50
     Hogwarts
    -0.49
    IsContent
    -0.49
    POSITIVE LOGITS
    glTexCoord
    0.54
     Relaciones
    0.38
    Médaille
    0.37
     novedad
    0.35
     EconPapers
    0.34
    épar
    0.34
     Producción
    0.33
     Inscrivez
    0.33
     normalidad
    0.33
     perfeitamente
    0.33
    Act Density 0.774%

    No Known Activations