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

    Neuronpedia

    INDEX
    Explanations

    ,name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     상
    -0.08
    更多的是
    -0.08
     Kling
    -0.07
     Cartesian
    -0.07
    骑士
    -0.07
     לילדים
    -0.07
     camouflage
    -0.07
     February
    -0.07
    楼上
    -0.07
    dig
    -0.07
    POSITIVE LOGITS
    去过
    0.08
    펍
    0.07
     diplomacy
    0.07
    슭
    0.07
    rose
    0.06
    IXEL
    0.06
     онл
    0.06
     stools
    0.06
    _almost
    0.06
     reversed
    0.06
    Act Density 0.001%

    No Known Activations