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
    579
    -0.07
     العل
    -0.06
     sett
    -0.06
     жил
    -0.06
     wyn
    -0.06
    刷
    -0.06
     MPG
    -0.06
     Luc
    -0.06
     rov
    -0.06
    変
    -0.06
    POSITIVE LOGITS
     inclined
    0.07
    igrate
    0.06
    mentioned
    0.06
     Mentor
    0.06
     Bölüm
    0.06
    *D
    0.06
     commonly
    0.06
    imshow
    0.06
     etm
    0.06
    _BUFF
    0.06
    Act Density 0.008%

    No Known Activations