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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     egy
    -0.08
     gastrointestinal
    -0.07
    /name
    -0.07
     tul
    -0.07
    Seconds
    -0.06
     případně
    -0.06
    人が
    -0.06
    ski
    -0.06
    ーリ
    -0.06
    your
    -0.06
    POSITIVE LOGITS
    _chan
    0.07
    <<<<<<<<
    0.06
     Csv
    0.06
     classname
    0.06
    \Middleware
    0.06
    .RequestMapping
    0.06
     screenSize
    0.06
    xCC
    0.06
     спе
    0.06
     intermedi
    0.06
    Act Density 0.029%

    No Known Activations