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

    Neuronpedia

    INDEX
    Explanations

    Big

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    有了
    -0.07
    류
    -0.07
    Ừ
    -0.07
    撰写
    -0.07
     urge
    -0.07
     fleeing
    -0.07
    欧盟
    -0.07
    Anchor
    -0.07
    _CHUNK
    -0.07
     refuse
    -0.07
    POSITIVE LOGITS
    一定会
    0.09
     dateFormat
    0.08
     pprint
    0.07
    简便
    0.07
     big
    0.07
     sophisticated
    0.07
    ív
    0.07
    пт
    0.07
     migr
    0.07
     Snapdragon
    0.07
    Act Density 0.037%

    No Known Activations