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

    Neuronpedia

    INDEX
    Explanations

    numerical references, particularly years

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

    day 21

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?,
    -0.31
     impersonal
    -0.29
    nek
    -0.28
     <<"
    -0.27
    blue
    -0.27
    fat
    -0.26
    ^{[
    -0.26
    dep
    -0.26
    glDelete
    -0.26
     Beweg
    -0.25
    POSITIVE LOGITS
     propOrder
    0.76
    ftagPool
    0.76
     transfieras
    0.66
    AddTagHelper
    0.65
     Chwiliwch
    0.59
    WithIOException
    0.58
    AccessorTable
    0.55
     indígen
    0.55
    findpost
    0.54
    GEBURTSDATUM
    0.54
    Act Density 0.008%

    No Known Activations