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
    ?\
    -0.06
    .return
    -0.06
     symmetric
    -0.06
    _TESTS
    -0.06
     disobed
    -0.06
    Driving
    -0.06
    这些
    -0.06
    ,&
    -0.05
     unsettling
    -0.05
    otionEvent
    -0.05
    POSITIVE LOGITS
     органов
    0.07
     سالم
    0.07
     getMessage
    0.06
     좀
    0.06
    ryfall
    0.06
     هن
    0.06
     Petro
    0.06
    UTF
    0.06
     ac
    0.06
     lead
    0.06
    Act Density 0.080%

    No Known Activations