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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ric
    -0.07
    dığında
    -0.07
    国家重点
    -0.07
    .have
    -0.06
    .Username
    -0.06
     got
    -0.06
    仅仅
    -0.06
    地理
    -0.06
     Susan
    -0.06
     identifier
    -0.06
    POSITIVE LOGITS
    NAV
    0.07
     nửa
    0.07
    _FACT
    0.07
     điều
    0.07
    衃
    0.07
    ए
    0.07
    _VAL
    0.06
    𫄨
    0.06
    ⚚
    0.06
    钣
    0.06
    Act Density 0.013%

    No Known Activations