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

    Neuronpedia

    INDEX
    Explanations

    Rants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucose
    -0.07
    純
    -0.06
    组
    -0.06
    ทร
    -0.06
     ACS
    -0.06
    یا
    -0.06
    ourcem
    -0.06
     позитив
    -0.06
    іст
    -0.06
    Claim
    -0.06
    POSITIVE LOGITS
     Outlet
    0.07
     Hedge
    0.06
    [((
    0.06
     Error
    0.06
    户
    0.06
    (html
    0.06
     Screens
    0.06
     komplex
    0.06
     Uruguay
    0.06
     Sosyal
    0.06
    Act Density 0.178%

    No Known Activations