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

    Neuronpedia

    INDEX
    Explanations

    references to specific characters and works in literature and film

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

    Follows capitalized words/names

    np_acts-logits-general · gemini-2.0-flash

    literary and operatic characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.71
    :✨
    -0.65
    tagext
    -0.61
    uldron
    -0.59
    lijst
    -0.56
    bibitem
    -0.55
    enterOuterAlt
    -0.54
    Viitteet
    -0.54
    دانشنامهٔ
    -0.53
    ientôt
    -0.52
    POSITIVE LOGITS
     himself
    0.75
     Himself
    0.68
     personaggio
    0.68
    himself
    0.60
     personaggi
    0.60
    requestCode
    0.56
    yargs
    0.55
     originais
    0.55
    DriverManager
    0.55
     déliv
    0.54
    Act Density 0.222%

    No Known Activations