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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mktime
    -0.06
     относят
    -0.06
     Cristina
    -0.06
    강
    -0.06
    首
    -0.06
     Modules
    -0.06
     完
    -0.06
     پاس
    -0.06
     закін
    -0.06
    interrupt
    -0.06
    POSITIVE LOGITS
     by
    0.10
    Bay
    0.08
     зависим
    0.07
    .ly
    0.07
     By
    0.06
    _BY
    0.06
     громадян
    0.06
    ổng
    0.06
    )sender
    0.06
    rastructure
    0.06
    Act Density 0.039%

    No Known Activations