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

    Neuronpedia

    INDEX
    Explanations

    quantitative assessments regarding acceptable limits and thresholds in various contexts

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

    Values exceeding or falling outside limits

    np_acts-logits-general · gemini-2.0-flash

    above or below a limit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.48
    thas
    -0.45
     рода
    -0.45
    forName
    -0.44
     druž
    -0.44
     doll
    -0.44
    addGroup
    -0.43
    באנגלית
    -0.43
    isle
    -0.39
    cektir
    -0.39
    POSITIVE LOGITS
     threshold
    0.73
     optimum
    0.70
     recommended
    0.70
     MUNDO
    0.69
    Embeddable
    0.68
     optimal
    0.68
    UnusedPrivate
    0.66
    RegistryLite
    0.66
    WarningLevel
    0.65
    oa̍t
    0.65
    Act Density 0.441%

    No Known Activations