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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aval
    -0.08
    userid
    -0.08
     registration
    -0.08
    -registration
    -0.07
     permits
    -0.07
     ati
    -0.07
     exams
    -0.07
     Somebody
    -0.07
     imin
    -0.07
     Registration
    -0.07
    POSITIVE LOGITS
     eher
    0.11
     vielmehr
    0.10
    む
    0.10
    的是
    0.09
    Rather
    0.09
     مجرد
    0.09
     всего
    0.09
     rather
    0.09
     скорее
    0.09
    乎
    0.09
    Act Density 0.042%

    No Known Activations