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

    Neuronpedia

    INDEX
    Explanations

    references to manual curation and annotation processes

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

    manual, human, hand-crafted processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.40
     avoient
    -0.38
     getAge
    -0.36
     feroit
    -0.36
     estadísticas
    -0.36
    abestanden
    -0.35
     crois
    -0.35
    исленность
    -0.35
     propTypes
    -0.34
    anthene
    -0.34
    POSITIVE LOGITS
     manually
    0.63
    ScopeManager
    0.52
    手动
    0.52
    Manually
    0.50
     Manually
    0.50
    脚注の使い方
    0.50
    adaptiveStyles
    0.49
     manual
    0.49
    ulemon
    0.48
    ècie
    0.48
    Act Density 0.212%

    No Known Activations