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

    Neuronpedia

    INDEX
    Explanations

    II

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Story
    -0.07
     mask
    -0.07
     tuple
    -0.07
    벽
    -0.07
    ków
    -0.07
     power
    -0.07
    power
    -0.07
    -bed
    -0.07
     Word
    -0.06
    37
    -0.06
    POSITIVE LOGITS
    #----------------------------------------------------------------------------
    0.06
    APIView
    0.06
     Panda
    0.06
    _membership
    0.06
    (pr
    0.06
     заверш
    0.06
    ^K
    0.06
    这样的
    0.06
    容易
    0.06
     sunglasses
    0.06
    Act Density 0.139%

    No Known Activations