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

    Neuronpedia

    INDEX
    Explanations

    conditional statements related to compliance and consequences

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

    arrests or bounties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tens
    -0.29
     évolution
    -0.29
     dirige
    -0.28
    ViewBag
    -0.28
     descenso
    -0.28
     dres
    -0.27
     especialidad
    -0.27
     milieux
    -0.26
    labus
    -0.26
     allora
    -0.26
    POSITIVE LOGITS
    genodigd
    0.63
    isContained
    0.61
    TagMode
    0.60
     ddelweddau
    0.59
    Архівовано
    0.59
     kasarigan
    0.55
     improperly
    0.55
    KommentareTeilen
    0.53
    anyone
    0.53
     dezelve
    0.52
    Act Density 0.047%

    No Known Activations