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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [label
    -0.07
     Attached
    -0.07
     laundry
    -0.07
    ochastic
    -0.07
    Local
    -0.07
     Local
    -0.06
     chronic
    -0.06
    670
    -0.06
     understand
    -0.06
     BA
    -0.06
    POSITIVE LOGITS
    URN
    0.06
     gaan
    0.06
    ได
    0.06
     adjud
    0.06
    ्शन
    0.06
     NSURL
    0.06
     ประ
    0.06
     чис
    0.06
     ferv
    0.06
     зг
    0.06
    Act Density 0.141%

    No Known Activations