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

    Neuronpedia

    INDEX
    Explanations

    software libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ut
    -0.07
     misdemean
    -0.06
     propagation
    -0.06
    ुआत
    -0.06
    ी.
    -0.06
    .black
    -0.06
     celle
    -0.06
    协
    -0.06
    -cultural
    -0.06
    歡
    -0.06
    POSITIVE LOGITS
     подум
    0.06
    BeforeEach
    0.06
    قع
    0.06
    Tuesday
    0.06
     ldb
    0.06
     Broncos
    0.06
     Shiite
    0.06
    ,’’
    0.06
    Written
    0.06
     біля
    0.06
    Act Density 0.017%

    No Known Activations