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

    Neuronpedia

    INDEX
    Explanations

    active verbs related to launching and ending events or actions

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

    process verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.44
    -0.42
    OCCURRED
    -0.42
    vosti
    -0.41
     lately
    -0.40
    spiller
    -0.40
    utilisons
    -0.40
     Depuis
    -0.40
    ✨:
    -0.39
     ongoing
    -0.38
    POSITIVE LOGITS
     ſta
    0.52
    queryInterface
    0.48
     abstrato
    0.48
     myſelf
    0.48
     pleaſure
    0.47
     elétrico
    0.47
     étoit
    0.47
     ſtand
    0.46
    featureID
    0.45
     direta
    0.45
    Act Density 0.072%

    No Known Activations