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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    완
    -0.07
     Manip
    -0.07
    bruary
    -0.06
     リ
    -0.06
    -svg
    -0.06
    Krist
    -0.06
    464
    -0.06
    Tail
    -0.06
     isAuthenticated
    -0.06
    ởi
    -0.06
    POSITIVE LOGITS
     trẻ
    0.07
    itives
    0.07
    (Table
    0.06
     měsíců
    0.06
    .Number
    0.06
     limite
    0.06
    los
    0.06
     setPage
    0.06
     admit
    0.06
     lider
    0.06
    Act Density 1.143%

    No Known Activations