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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proble
    -0.06
     authored
    -0.06
     ноя
    -0.06
     IDb
    -0.06
    Sele
    -0.06
    ालन
    -0.06
    ’dan
    -0.06
     görmek
    -0.06
     encontrado
    -0.06
     سرمایه
    -0.06
    POSITIVE LOGITS
    กว
    0.07
    (jTextField
    0.07
     richTextBox
    0.07
     distraction
    0.06
    (write
    0.06
     Mono
    0.06
    coin
    0.06
    To
    0.06
    --↵
    0.06
    Es
    0.06
    Act Density 0.015%

    No Known Activations