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

    Neuronpedia

    INDEX
    Explanations

    mentions of New York City, especially Brooklyn and Manhattan, as well as contextual words like "in" "to" and words denoting artistic activity.

    oai_token-act-pair · gemini-2.0-flash

    New York City

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الحره
    -0.98
    Personensuche
    -0.88
    ftagPool
    -0.83
    MetaObject
    -0.79
    MessageTagHelper
    -0.73
    MemoryWarning
    -0.71
    ///</
    -0.70
     typelib
    -0.68
     صوتيه
    -0.67
    ParallelGroup
    -0.66
    POSITIVE LOGITS
     Nol
    0.55
     Gow
    0.52
    Tri
    0.50
     Tri
    0.49
    yectos
    0.48
     Lower
    0.48
    Duane
    0.46
     Dum
    0.45
    cotta
    0.45
    Lower
    0.44
    Act Density 1.000%

    No Known Activations