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

    Neuronpedia

    INDEX
    Explanations

    references to downtown areas

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

    downtown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yaiba
    -0.61
     étoit
    -0.55
     avoit
    -0.54
    cessite
    -0.50
     dieß
    -0.49
    ceptre
    -0.49
     '\\;'
    -0.49
     propOrder
    -0.48
     auroit
    -0.48
     Bekasi
    -0.46
    POSITIVE LOGITS
     downtown
    1.10
     Downtown
    1.03
    downtown
    0.97
    Downtown
    0.94
     للاسماء
    0.67
    AnchorStyles
    0.59
     فريبيس
    0.55
     downstairs
    0.52
     Dumont
    0.52
     DOWN
    0.51
    Act Density 0.001%

    No Known Activations