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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ambassador
    -0.07
     widgets
    -0.07
    ывать
    -0.07
    Expect
    -0.06
     jejichž
    -0.06
     SVM
    -0.06
    찌
    -0.06
    .all
    -0.06
    ать
    -0.06
    ζε
    -0.06
    POSITIVE LOGITS
     dildo
    0.07
    cannot
    0.06
    scribers
    0.06
     Detect
    0.06
    _orig
    0.06
    Law
    0.06
    _original
    0.06
     Narr
    0.06
    ریم
    0.06
    regist
    0.06
    Act Density 0.010%

    No Known Activations