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

    Neuronpedia

    INDEX
    Explanations

    instances of document formatting and LaTeX command structures

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

    end of document or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bewußt
    -0.46
     électroniques
    -0.42
     mecán
    -0.41
     dignidad
    -0.40
     totalidad
    -0.40
    <?
    -0.39
     dignité
    -0.39
     blessés
    -0.39
     médicaux
    -0.39
     leeftijd
    -0.38
    POSITIVE LOGITS
     تضيفلها
    0.63
    UnknownFields
    0.61
    iforms
    0.59
    NAV
    0.58
     NAV
    0.56
    StructEnd
    0.56
    Hush
    0.56
     nave
    0.56
    ISupport
    0.55
     navel
    0.55
    Act Density 0.006%

    No Known Activations