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

    Neuronpedia

    INDEX
    Explanations

    Code/Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifrån
    -0.09
     Ideally
    -0.09
     impartial
    -0.09
     cruc
    -0.09
     ungef
    -0.09
     относительно
    -0.08
    NAP
    -0.08
     außerdem
    -0.08
     Essentially
    -0.08
     хоть
    -0.08
    POSITIVE LOGITS
     
    0.08
     sided
    0.07
    490
    0.07
    กัน
    0.07
     complicated
    0.07
    \↵
    0.07
     فإن
    0.07
     subsystem
    0.07
    ,↵↵
    0.07
    (program
    0.07
    Act Density 0.025%

    No Known Activations