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

    Neuronpedia

    INDEX
    Explanations

    Code and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ême
    -0.07
    rances
    -0.06
     packs
    -0.06
    pes
    -0.06
     prv
    -0.06
    WASHINGTON
    -0.06
    .replace
    -0.06
    фік
    -0.06
    patrick
    -0.06
    变化
    -0.06
    POSITIVE LOGITS
     Soph
    0.07
    EQUAL
    0.06
     Báo
    0.06
     Makeup
    0.06
    SignUp
    0.06
     uphol
    0.06
     Things
    0.06
     Alexandra
    0.06
     البي
    0.06
     [&](
    0.06
    Act Density 0.136%

    No Known Activations