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

    Neuronpedia

    INDEX
    Explanations

    phrases related to choices and decisions

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

    concerning, regarding, aspect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.61
     للمعارف
    -0.59
    RTEE
    -0.59
     geſch
    -0.57
     deſſen
    -0.56
    UrlResolution
    -0.56
     fubject
    -0.56
     pleaſure
    -0.55
    contentLoaded
    -0.55
     ſte
    -0.55
    POSITIVE LOGITS
     dotyczące
    0.35
     nogal
    0.34
     فريبيس
    0.33
    oggetto
    0.32
     urusan
    0.32
     vectorielle
    0.32
    aspetto
    0.31
     décisions
    0.29
     didalam
    0.28
     miejsce
    0.28
    Act Density 0.012%

    No Known Activations