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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     primes
    -0.07
     combating
    -0.06
    lemen
    -0.06
    ccb
    -0.06
     Whit
    -0.06
     Witt
    -0.06
     atleast
    -0.06
    orry
    -0.05
    uele
    -0.05
    —but
    -0.05
    POSITIVE LOGITS
    压
    0.09
     Дем
    0.07
    壓
    0.07
     six
    0.07
    3
    0.07
    퍼
    0.07
    2
    0.06
     unordered
    0.06
    ('|
    0.06
    18
    0.06
    Act Density 0.058%

    No Known Activations