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

    Neuronpedia

    INDEX
    Explanations

    components and comparisons in technical or formal contexts

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

    [token] + "-ing" form of a verb

    np_acts-logits-general · gemini-2.0-flash

    describing states or ongoing conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fabrique
    -0.55
     sambung
    -0.52
     varsa
    -0.52
     stället
    -0.51
     puissent
    -0.50
     dapatkan
    -0.50
    度は
    -0.50
     gangen
    -0.49
     diperlukan
    -0.49
     dibutuhkan
    -0.48
    POSITIVE LOGITS
     being
    1.96
     having
    1.77
    being
    1.59
     fiind
    1.54
     needing
    1.54
    having
    1.45
     requiring
    1.45
     étant
    1.42
     becoming
    1.35
     BEING
    1.29
    Act Density 0.590%

    No Known Activations