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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    那里
    -0.07
    kům
    -0.07
    στρο
    -0.07
    otive
    -0.07
     coop
    -0.07
    .Reset
    -0.06
    xAE
    -0.06
    ออกแบบ
    -0.06
     pás
    -0.06
    Image
    -0.06
    POSITIVE LOGITS
    links
    0.06
     Williams
    0.06
     CENT
    0.06
     historians
    0.06
    avenous
    0.05
    alesce
    0.05
     Cv
    0.05
    GES
    0.05
     curled
    0.05
     definitive
    0.05
    Act Density 0.272%

    No Known Activations