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

    Neuronpedia

    INDEX
    Explanations

    references to individual items or entities within various contexts

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

    individual entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.96
    GEBURTSDATUM
    -0.69
    adaptiveStyles
    -0.68
    Hentet
    -0.68
    IntoConstraints
    -0.63
    Хьажоргаш
    -0.63
     препратки
    -0.62
     linkovi
    -0.61
     EconPapers
    -0.60
    twimg
    -0.59
    POSITIVE LOGITS
     individual
    1.63
    Individual
    1.48
    individual
    1.44
     Individual
    1.41
     individuale
    1.37
     individually
    1.36
     individuales
    1.29
     INDIVIDUAL
    1.25
     individuel
    1.19
     individuelles
    1.19
    Act Density 0.064%

    No Known Activations