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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or sequences related to timing and order

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

    time offset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jîn
    -0.48
     zoude
    -0.46
    CppMethod
    -0.45
    XmlAccessorType
    -0.43
    Hauptartikel
    -0.42
    badan
    -0.41
    Ārējās
    -0.41
    interopRequire
    -0.41
    boneca
    -0.40
    Ligações
    -0.39
    POSITIVE LOGITS
     delayed
    0.72
    delayed
    0.64
    Delayed
    0.59
     Delayed
    0.58
     delay
    0.58
     delaying
    0.57
    Delay
    0.55
     Delay
    0.52
     delays
    0.50
     DELAY
    0.50
    Act Density 0.133%

    No Known Activations