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

    Neuronpedia

    INDEX
    Explanations

    senior junior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вывод
    -0.07
    heid
    -0.07
     escrit
    -0.07
    >No
    -0.06
     MainWindow
    -0.06
    ssid
    -0.06
    ipp
    -0.06
     executing
    -0.06
     unstable
    -0.06
    eya
    -0.06
    POSITIVE LOGITS
    �
    0.07
     feminists
    0.06
    ریه
    0.06
    تز
    0.06
    (config
    0.06
     puppy
    0.06
    Netflix
    0.06
     stub
    0.06
     маст
    0.06
     bis
    0.06
    Act Density 0.004%

    No Known Activations