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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate uncertainty, personal opinion, or requests for clarification

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

    Code, programming, and technical language

    np_acts-logits-general · gemini-2.0-flash

    programming code and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.66
     оригіналу
    -0.49
     HasFactory
    -0.48
     صوتيه
    -0.48
     TestBed
    -0.46
    KommentareTeilen
    -0.44
    bitField
    -0.44
    ThroughAttribute
    -0.44
     שוליים
    -0.44
    tagHelperRunner
    -0.42
    POSITIVE LOGITS
     Freya
    0.44
     Thiago
    0.41
    endregion
    0.41
    ']))
    0.40
    ']]
    0.40
     Aladdin
    0.40
     gira
    0.39
     sé
    0.39
    ']],
    0.39
    цездатний
    0.39
    Act Density 0.542%

    No Known Activations