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

    Neuronpedia

    INDEX
    Explanations

    Ki

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sàng
    -0.08
     suscept
    -0.08
    /↵↵↵↵
    -0.07
     فهي
    -0.07
    好奇心
    -0.07
     thaimassage
    -0.07
    .setView
    -0.07
    💛
    -0.07
     llen
    -0.07
     ora
    -0.07
    POSITIVE LOGITS
    ificantly
    0.07
     Lik
    0.07
     deterior
    0.07
    _serial
    0.07
    滨
    0.07
     Teen
    0.07
     Kil
    0.06
    _peak
    0.06
     revived
    0.06
    Pri
    0.06
    Act Density 0.002%

    No Known Activations