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

    Neuronpedia

    INDEX
    Explanations

    the presence of special formatting indicators for document or code structure

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

    LaTeX math mode

    np_acts-logits-general · gemini-2.0-flash

    math and greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.64
    WebElementEntity
    -0.63
    ſelves
    -0.54
     houſe
    -0.52
     iſt
    -0.51
    verwijspagina
    -0.50
     arşivlendi
    -0.48
     HasFactory
    -0.47
     myſelf
    -0.47
     Houſe
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.57
    es
    0.51
     rely
    0.49
     Freitas
    0.49
     baby
    0.48
    :
    0.48
    ity
    0.48
    kowych
    0.47
    ES
    0.46
    UnusedPrivate
    0.46
    Act Density 0.664%

    No Known Activations