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

    Neuronpedia

    INDEX
    Explanations

    labels or markers in structured documents, such as equations or sections

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

    Followed by an equation label

    np_acts-logits-general · gemini-2.0-flash

    LaTeX labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    îtra
    -0.63
    ícil
    -0.60
    Kanpo
    -0.55
    MessageTagHelper
    -0.55
    picasso
    -0.53
    ^[
    -0.53
    endcsname
    -0.52
     comp
    -0.52
    ()->
    -0.51
    uxxxx
    -0.51
    POSITIVE LOGITS
    addComponent
    1.71
    ParallelGroup
    0.75
    IContainer
    0.71
     Inaug
    0.66
     ARXIV
    0.64
    findpost
    0.61
    UnusedPrivate
    0.61
     myſelf
    0.60
    Lesen
    0.58
    inaug
    0.58
    Act Density 0.027%

    No Known Activations