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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    っ
    -0.07
    拼搏
    -0.07
    五六
    -0.07
    sleep
    -0.07
    тельного
    -0.07
    jpg
    -0.07
    _transaksi
    -0.07
    _RETURNTRANSFER
    -0.07
     Arial
    -0.07
    -eng
    -0.07
    POSITIVE LOGITS
     reminder
    0.07
    _subset
    0.07
    .export
    0.07
     Saved
    0.07
     Doom
    0.07
     сет
    0.07
    硙
    0.07
    Lost
    0.07
     Wool
    0.06
    declar
    0.06
    Act Density 0.002%

    No Known Activations