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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities, particularly pronouns and their antecedents

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

    it because or it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     egne
    -0.42
    請繼續往下閱讀
    -0.35
    Bibliograf
    -0.34
     fijar
    -0.33
     desglose
    -0.32
    }+$
    -0.32
     repetir
    -0.32
    ̈́
    -0.32
     výbě
    -0.32
     múltiples
    -0.31
    POSITIVE LOGITS
     GenerationType
    0.55
    MathML
    0.54
     Officers
    0.52
    AlterField
    0.50
    Fraser
    0.50
    ?
    0.49
     Wikispecies
    0.48
    Officers
    0.48
    Savage
    0.47
     Вікі
    0.47
    Act Density 0.064%

    No Known Activations