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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PIO
    -0.08
     cout
    -0.07
     선
    -0.06
    _COLS
    -0.06
     responseObject
    -0.06
     mating
    -0.06
    .heap
    -0.06
     Aside
    -0.06
     Chúng
    -0.06
    _Window
    -0.06
    POSITIVE LOGITS
    ically
    0.07
    thesized
    0.07
    äsent
    0.06
    (loc
    0.06
     خدا
    0.06
    ical
    0.06
     sunshine
    0.06
    ников
    0.06
    embrance
    0.06
    302
    0.06
    Act Density 0.023%

    No Known Activations