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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    הזמנה
    -0.07
    ἷ
    -0.06
    想必
    -0.06
    飙升
    -0.06
     Emm
    -0.06
     Excel
    -0.06
    azes
    -0.06
     knockout
    -0.06
    هز
    -0.06
    .reducer
    -0.06
    POSITIVE LOGITS
     teach
    0.07
    取决于
    0.06
    _ed
    0.06
    may
    0.06
    .Col
    0.06
    Vac
    0.06
     mark
    0.06
    _coverage
    0.06
     prepaid
    0.06
    eli
    0.06
    Act Density 0.302%

    No Known Activations