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

    Neuronpedia

    INDEX
    Explanations

    released

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    znik
    -0.07
    γκ
    -0.06
     chân
    -0.06
    _catalog
    -0.06
    URE
    -0.06
    _sm
    -0.06
     MODE
    -0.06
    clusions
    -0.06
    kách
    -0.06
     Packing
    -0.06
    POSITIVE LOGITS
     đị
    0.07
     releases
    0.07
    像是
    0.07
     diabetic
    0.07
     vacancies
    0.06
    (metric
    0.06
     racket
    0.06
    Ui
    0.06
    \Event
    0.06
     Tau
    0.06
    Act Density 0.011%

    No Known Activations