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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recurrence or variation in subject matter

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

    official public, Totally Valid, very extensive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.60
    posedge
    -0.54
     kasarigan
    -0.54
    queryInterface
    -0.52
     ویکی‌پدی
    -0.50
    SharedCtor
    -0.50
    IsMutable
    -0.49
    BeginContext
    -0.48
    TagMode
    -0.48
    SourceChecksum
    -0.46
    POSITIVE LOGITS
     thingy
    0.40
    qrstuvwxyz
    0.38
     stuff
    0.37
     kinda
    0.36
    stuff
    0.35
     sorta
    0.35
     настоя
    0.34
     definiti
    0.33
     okuyayım
    0.33
    ₁(
    0.33
    Act Density 0.046%

    No Known Activations