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

    Neuronpedia

    INDEX
    Explanations

    uned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ан
    -0.07
    oren
    -0.07
    ropp
    -0.07
    Hour
    -0.07
     Chem
    -0.06
    Compound
    -0.06
    Buf
    -0.06
     goose
    -0.06
    ogenic
    -0.06
     peptide
    -0.06
    POSITIVE LOGITS
     έχουν
    0.07
    Pref
    0.07
    ै।↵
    0.06
     Inhal
    0.06
     Ні
    0.06
    realDonaldTrump
    0.06
     Usuario
    0.06
     مواطنة
    0.06
     ""));↵
    0.06
    配置
    0.06
    Act Density 0.055%

    No Known Activations