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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANDROID
    -0.08
     tướng
    -0.07
     numbers
    -0.07
     когда
    -0.06
     resolved
    -0.06
    pora
    -0.06
     امن
    -0.06
    .trip
    -0.06
     ELSE
    -0.06
     THREAD
    -0.06
    POSITIVE LOGITS
    setSize
    0.07
     Τι
    0.06
     Closet
    0.06
     thrust
    0.06
    �
    0.06
    rezent
    0.06
    :@"%@
    0.06
     salle
    0.06
    rana
    0.06
    лся
    0.06
    Act Density 0.064%

    No Known Activations