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

    Neuronpedia

    INDEX
    Explanations

    code and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    ན
    -0.07
    خوف
    -0.07
    棋牌游戏
    -0.07
    続きを読む
    -0.06
    [:,
    -0.06
    _YES
    -0.06
     attenuation
    -0.06
     sân
    -0.06
    Night
    -0.06
    POSITIVE LOGITS
    Layout
    0.07
     handling
    0.07
     Locale
    0.07
    ()]
    0.07
     INC
    0.07
    inclusive
    0.07
    itage
    0.06
     asses
    0.06
     bottle
    0.06
    Cases
    0.06
    Act Density 0.009%

    No Known Activations