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

    Neuronpedia

    INDEX
    Explanations

    edition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cub
    -0.06
    FFF
    -0.06
    ']=='
    -0.06
     urn
    -0.06
     ful
    -0.06
    enth
    -0.06
     shared
    -0.06
     covid
    -0.06
    -half
    -0.06
    =com
    -0.06
    POSITIVE LOGITS
    iều
    0.07
     výraz
    0.07
     çı
    0.07
    playing
    0.07
     금
    0.07
     WikiLeaks
    0.06
    Appe
    0.06
    ondere
    0.06
    epam
    0.06
     belang
    0.06
    Act Density 0.011%

    No Known Activations