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

    Neuronpedia

    INDEX
    Explanations

    generating function, characteristic function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     диск
    -0.08
    ancell
    -0.08
     جامعه
    -0.08
    巡视
    -0.08
     shown
    -0.08
     illustrated
    -0.08
     लिखा
    -0.08
     tape
    -0.08
     قانونی
    -0.08
     femen
    -0.07
    POSITIVE LOGITS
    기의
    0.08
     Loving
    0.08
    urpose
    0.07
     rek
    0.07
     소재
    0.07
     nests
    0.07
    র্ম
    0.07
    %D
    0.07
    IAS
    0.07
    �
    0.07
    Act Density 0.002%

    No Known Activations