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

    Neuronpedia

    INDEX
    Explanations

    single-digit integers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     روابط
    -0.06
    (grad
    -0.06
     doubted
    -0.06
    िथ
    -0.06
    BSD
    -0.06
     Paging
    -0.06
    สอบ
    -0.06
    gni
    -0.06
    ्व
    -0.06
         
    -0.06
    POSITIVE LOGITS
     elite
    0.07
     Scottish
    0.07
    hana
    0.06
    ustrial
    0.06
    _wp
    0.06
    ,l
    0.06
    _gb
    0.06
     jan
    0.06
    (dat
    0.06
     oblig
    0.06
    Act Density 0.004%

    No Known Activations