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

    Neuronpedia

    INDEX
    Explanations

    formal notifications or reminders regarding policy changes and updates

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

    Official announcements or notices

    np_acts-logits-general · gemini-2.0-flash

    announcements and pending matters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.45
    MouseAdapter
    -0.45
    TagMode
    -0.44
    ViewInit
    -0.42
    fjspx
    -0.41
     buzz
    -0.40
     concepts
    -0.40
    concepts
    -0.40
     оригіналу
    -0.39
     Exactos
    -0.39
    POSITIVE LOGITS
     indefinitely
    0.49
     please
    0.46
     termica
    0.45
    دانشنامهٔ
    0.45
     Announcement
    0.45
     announced
    0.45
     henceforth
    0.45
    Please
    0.44
     कृपया
    0.44
    ↹
    0.43
    Act Density 0.214%

    No Known Activations