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

    Neuronpedia

    INDEX
    Explanations

    expressions of introspection and emotional complexity

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

    positive experiences and qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.63
     חיצוניים
    -0.59
    #+#
    -0.58
    GEBURTSDATUM
    -0.57
     disambiguazione
    -0.57
    PendingIntent
    -0.56
    GeneratedMessage
    -0.56
     nakalista
    -0.56
    migrationBuilder
    -0.55
    참고
    -0.55
    POSITIVE LOGITS
    styleType
    0.35
     daher
    0.33
    hence
    0.33
     dislike
    0.32
     hence
    0.31
     crappy
    0.30
    osoba
    0.30
    ItemBackground
    0.30
    oarece
    0.30
     nasty
    0.29
    Act Density 0.715%

    No Known Activations