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

    Neuronpedia

    INDEX
    Explanations

    key elements of studies or tests assessing health-related information and their validation

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

    contradictory conjunctions indicating exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.61
     ujednoznacz
    -0.52
    ContentAsync
    -0.51
    SequentialGroup
    -0.50
     strtok
    -0.49
    Aiheesta
    -0.48
    AsUp
    -0.46
     referrerpolicy
    -0.46
    MLLoader
    -0.46
    ScopeManager
    -0.44
    POSITIVE LOGITS
     trustworthy
    0.61
     reputable
    0.54
     credible
    0.50
     razonable
    0.49
     reliable
    0.48
     trusted
    0.48
     trustworthiness
    0.47
    trust
    0.47
     credibility
    0.47
    可靠
    0.45
    Act Density 0.085%

    No Known Activations