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

    Neuronpedia

    INDEX
    Explanations

    reference numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (@(
    -0.06
     prostitutas
    -0.06
    (ver
    -0.06
    itura
    -0.06
    退
    -0.06
    叔
    -0.06
    直播
    -0.06
    .Core
    -0.06
     fal
    -0.06
    ाओ
    -0.06
    POSITIVE LOGITS
     SAM
    0.08
     synthes
    0.07
    avigation
    0.07
     workbook
    0.06
     dissip
    0.06
    Pokemon
    0.06
     Spark
    0.06
    -ev
    0.06
     emailed
    0.06
    ucker
    0.06
    Act Density 0.012%

    No Known Activations