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

    Neuronpedia

    INDEX
    Explanations

    references to statements or discussions about opinions and beliefs

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

    what they said or wrote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.70
     disambiguazione
    -0.56
     arşivlendi
    -0.53
    MigrationBuilder
    -0.52
    stdc
    -0.52
    SourceChecksum
    -0.51
     VIDEOT
    -0.50
    ronpa
    -0.48
    bootstrapcdn
    -0.47
    Хьажоргаш
    -0.47
    POSITIVE LOGITS
     statements
    0.46
     lời
    0.45
     speech
    0.42
     discorso
    0.40
     صحبت
    0.40
     statement
    0.39
     حرف
    0.39
     كلام
    0.39
     conversation
    0.38
    His
    0.36
    Act Density 0.093%

    No Known Activations