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

    Neuronpedia

    INDEX
    Explanations

    references and citation markers typically used in academic writing

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

    foreign language acronyms and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.71
     <<<<<<<<<<<<<<
    -0.66
     Taktlose
    -0.63
    Xna
    -0.59
     CURIAM
    -0.53
    writerow
    -0.53
    endmodule
    -0.52
    UnusedPrivate
    -0.52
    chyma
    -0.50
     OMITBAD
    -0.50
    POSITIVE LOGITS
    WebElementEntity
    0.40
    équipement
    0.39
    ômetro
    0.31
     mø
    0.30
     équipement
    0.29
    <!--[
    0.29
    Péri
    0.29
    hyrchwyd
    0.29
     współ
    0.28
     méta
    0.28
    Act Density 0.145%

    No Known Activations