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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    忆
    -0.08
    rl
    -0.07
    战胜
    -0.07
    那段
    -0.06
     underage
    -0.06
     Swarm
    -0.06
    小区
    -0.06
    趁
    -0.06
    /fontawesome
    -0.06
     domestically
    -0.06
    POSITIVE LOGITS
    publisher
    0.07
    褒
    0.07
     rune
    0.07
     William
    0.06
    True
    0.06
     proposed
    0.06
     Revised
    0.06
    illac
    0.06
    /fs
    0.06
    시키
    0.06
    Act Density 0.021%

    No Known Activations