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

    Neuronpedia

    INDEX
    Explanations

    references to English language and culture

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

    English language contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rootScope
    -0.42
    getHours
    -0.39
    .*")]
    -0.39
    Affiliations
    -0.38
    Referencies
    -0.38
     peak
    -0.37
     plaat
    -0.37
     Pohl
    -0.37
    PROTOBUF
    -0.36
     onts
    -0.36
    POSITIVE LOGITS
     English
    1.25
    English
    1.18
     ENGLISH
    1.07
    english
    1.00
     english
    1.00
    ENGLISH
    0.97
     Englishman
    0.88
     engelsk
    0.83
     inglês
    0.83
     anglaise
    0.82
    Act Density 0.018%

    No Known Activations