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

    Neuronpedia

    INDEX
    Explanations

    legal documents, colloquialisms, and words indicating positive sentiment.

    oai_token-act-pair · gemini-2.0-flash

    coding/legal text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     at
    -2.53
     At
    -2.16
    At
    -2.06
    at
    -1.80
     AT
    -1.47
     tại
    -1.17
    AtIndex
    -1.04
    AT
    -1.00
    Tại
    -0.92
    앳
    -0.89
    POSITIVE LOGITS
    PerformLayout
    0.57
    encodeWith
    0.52
    AsUp
    0.50
    DatabaseError
    0.47
    ниях
    0.46
    parseColor
    0.46
     Wicidata
    0.44
     kaynağından
    0.44
     répondit
    0.44
    hawatir
    0.43
    Act Density 1.987%

    No Known Activations