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

    Neuronpedia

    INDEX
    Explanations

    Reuters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     baş
    -0.07
     kitty
    -0.06
     Gund
    -0.06
     díl
    -0.06
    edom
    -0.06
     MEN
    -0.06
     domu
    -0.06
    Ui
    -0.06
     fName
    -0.06
     (++
    -0.06
    POSITIVE LOGITS
    映画
    0.07
     inflater
    0.07
    [R
    0.07
     precision
    0.06
     utter
    0.06
     faux
    0.06
    _refptr
    0.06
     Revelation
    0.06
    .UserInfo
    0.06
     reference
    0.06
    Act Density 0.001%

    No Known Activations