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

    Neuronpedia

    INDEX
    Explanations

    elements related to typesetting and formatting in documents

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

    latex formatting commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.47
     com
    -0.45
     ala
    -0.45
    Com
    -0.44
     comm
    -0.44
    Pla
    -0.43
     FIC
    -0.43
     from
    -0.43
    ://
    -0.43
     Kom
    -0.42
    POSITIVE LOGITS
    OGND
    0.82
     vixion
    0.69
     disponibilités
    0.68
    :✨
    0.64
     saveiro
    0.63
     wikipagina
    0.63
     indígen
    0.63
     Infór
    0.63
     mijne
    0.62
    boneca
    0.61
    Act Density 0.234%

    No Known Activations