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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    放在
    -0.07
    "...
    -0.07
    /q
    -0.07
     MT
    -0.06
     stimulation
    -0.06
    -fluid
    -0.06
     Phrase
    -0.06
     r
    -0.06
    )},
    -0.06
    -com
    -0.06
    POSITIVE LOGITS
     bánh
    0.07
     χρη
    0.06
     Tại
    0.06
     Rutgers
    0.06
    Δεν
    0.06
     memset
    0.06
    racuse
    0.06
    :type
    0.06
    Als
    0.06
    逸
    0.06
    Act Density 0.037%

    No Known Activations