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

    Neuronpedia

    INDEX
    Explanations

    SQL queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    直属
    -0.07
    .ru
    -0.07
     license
    -0.07
    背后
    -0.06
    _ELEMENTS
    -0.06
    Bei
    -0.06
    גדול
    -0.06
    _FORWARD
    -0.06
    TÜ
    -0.06
    RU
    -0.06
    POSITIVE LOGITS
    该案
    0.08
    摆
    0.07
     mAdapter
    0.07
     assignment
    0.07
     Probe
    0.06
    什么叫
    0.06
     mix
    0.06
     strategy
    0.06
    父亲
    0.06
     predic
    0.06
    Act Density 0.037%

    No Known Activations