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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to time and duration

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

    LaTeX equations and formatting

    np_acts-logits-general · gemini-2.0-flash

    equations following "disc" or mathematical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -1.26
     kasarigan
    -1.20
    rungsseite
    -1.11
    SourceChecksum
    -1.07
     Biôgrafia
    -1.05
     otomatig
    -1.03
     Италијани
    -1.02
    دانشنامهٔ
    -1.00
    invokeLater
    -0.99
    ArrowToggle
    -0.98
    POSITIVE LOGITS
     rowspan
    0.59
    [toxicity=0]
    0.59
    {~
    0.52
    жте
    0.49
    {
    0.45
    ‍
    0.44
    anglicky
    0.42
    <blockquote>
    0.41
    :%.
    0.41
    <strong>
    0.40
    Act Density 0.681%

    No Known Activations