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

    Neuronpedia

    INDEX
    Explanations

    double

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    精心
    -0.07
    潾
    -0.07
    时时
    -0.07
     الجميع
    -0.07
     gar
    -0.07
     mình
    -0.07
    哪裡
    -0.06
    议事
    -0.06
    _clusters
    -0.06
    变更
    -0.06
    POSITIVE LOGITS
    헉
    0.08
    andscape
    0.07
    альных
    0.07
    jak
    0.07
     patriarch
    0.07
     sweating
    0.07
     membrane
    0.07
    банк
    0.07
     draining
    0.07
    的女人
    0.07
    Act Density 0.002%

    No Known Activations