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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aggregates
    -0.07
    _Menu
    -0.06
    fect
    -0.06
    泡
    -0.06
     Ders
    -0.06
    unifu
    -0.06
    Demon
    -0.06
    bjerg
    -0.06
    Важ
    -0.06
    grades
    -0.06
    POSITIVE LOGITS
     probation
    0.07
    LINE
    0.07
    kır
    0.07
     practicing
    0.07
     Δι
    0.07
    tuğ
    0.06
    <location
    0.06
     Πολι
    0.06
     traced
    0.06
    lemek
    0.06
    Act Density 0.001%

    No Known Activations