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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     setw
    -0.07
     ब
    -0.07
    병
    -0.06
    719
    -0.06
     MethodInvocation
    -0.06
     trở
    -0.06
     terk
    -0.06
     tráv
    -0.06
     TreeSet
    -0.06
    .ReadKey
    -0.06
    POSITIVE LOGITS
    idan
    0.07
     Razor
    0.07
     Unc
    0.07
     aqui
    0.06
     batches
    0.06
     DOWNLOAD
    0.06
     gardens
    0.06
    nesota
    0.06
    ifest
    0.06
    LIK
    0.06
    Act Density 0.003%

    No Known Activations