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

    Neuronpedia

    INDEX
    Explanations

    role

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    server
    -0.06
    .py
    -0.06
     prost
    -0.06
    廳
    -0.06
    ура
    -0.06
     Deaths
    -0.06
    /by
    -0.06
     xem
    -0.06
     epis
    -0.06
    érique
    -0.06
    POSITIVE LOGITS
     Imp
    0.06
    基于
    0.06
     Shake
    0.06
    VG
    0.06
    Translations
    0.06
     Ledger
    0.06
     Chlor
    0.06
     Regular
    0.06
     prophet
    0.06
     Common
    0.06
    Act Density 0.050%

    No Known Activations