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

    Neuronpedia

    INDEX
    Explanations

    mathematical and structural representations of data

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

    patterns related to data structure or programming functions

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

    mathematical expressions with total

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ExtendWith
    -0.64
     المعيارى
    -0.64
     '\\;'
    -0.52
    RunWith
    -0.51
    vais
    -0.50
     blest
    -0.49
    TextHelper
    -0.48
    IsContent
    -0.46
     Virgo
    -0.45
    ελ
    -0.45
    POSITIVE LOGITS
    protoimpl
    0.73
     iVar
    0.64
    GEBURTSDATUM
    0.55
    Hentet
    0.55
     famí
    0.55
    Atsauces
    0.54
     ProtoMessage
    0.54
    xhttp
    0.52
    Hauptartikel
    0.52
    bitol
    0.51
    Act Density 0.091%

    No Known Activations