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

    Neuronpedia

    INDEX
    Explanations

    references to medical studies or research findings related to health and treatment outcomes

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

    Citations/references (e.g., ^[@ref135]^)

    np_acts-logits-general · gemini-2.0-flash

    citation and reference markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     always
    -0.69
     never
    -0.60
    always
    -0.52
    Always
    -0.51
     всегда
    -0.51
     Always
    -0.49
     sempre
    -0.48
     siempre
    -0.48
     תמיד
    -0.48
     alltid
    -0.47
    POSITIVE LOGITS
    KommentareTeilen
    0.59
     kasarigan
    0.58
     ویکی‌آمباردا
    0.55
    Viungo
    0.54
    thâu
    0.54
    Personensuche
    0.53
     createSprite
    0.51
    🔕
    0.50
     Hygien
    0.50
    GenerationType
    0.50
    Act Density 0.739%

    No Known Activations