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

    Neuronpedia

    INDEX
    Explanations

    parentheses and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ErrorHandler
    -0.06
    プリ
    -0.06
     Turn
    -0.06
     downloader
    -0.06
    _ANS
    -0.06
    Mahon
    -0.06
     pdu
    -0.05
    _until
    -0.05
     Marilyn
    -0.05
     οπο
    -0.05
    POSITIVE LOGITS
    (Order
    0.07
     intestinal
    0.07
     преп
    0.07
     offic
    0.07
    XXXX
    0.07
    률
    0.06
    #index
    0.06
     ';'
    0.06
    !/
    0.06
    endphp
    0.06
    Act Density 0.020%

    No Known Activations