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

    Neuronpedia

    INDEX
    Explanations

    identifiers and technical terms related to programming or data structures

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

    code libraries and aliases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -1.05
    findpost
    -1.00
    yarnpkg
    -0.87
    PMailer
    -0.84
    localctx
    -0.84
    uxxxx
    -0.81
     Roskov
    -0.80
    twimg
    -0.79
     محفوظة
    -0.79
    Hozzáférés
    -0.78
    POSITIVE LOGITS
    .
    0.35
    SceneManagement
    0.34
     peuples
    0.31
     symboles
    0.30
     pères
    0.29
    ;
    0.29
    )
    0.29
     pédagog
    0.29
     carottes
    0.28
     preuves
    0.28
    Act Density 0.026%

    No Known Activations