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

    Neuronpedia

    INDEX
    Explanations

    Last

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    azeera
    -0.09
    _continue
    -0.07
     يؤدي
    -0.07
    跑
    -0.07
    anye
    -0.07
    _CHIP
    -0.07
     autoComplete
    -0.07
    叶
    -0.07
    _ACTIVE
    -0.07
    而这
    -0.06
    POSITIVE LOGITS
    秋冬
    0.07
     ammunition
    0.07
     pri
    0.07
     schem
    0.07
    including
    0.07
    imin
    0.07
     sum
    0.07
     bibli
    0.07
    ecess
    0.06
    eff
    0.06
    Act Density 0.006%

    No Known Activations