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

    Neuronpedia

    INDEX
    Explanations

    possessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Zh
    -0.07
     господар
    -0.07
    pletely
    -0.07
     Yi
    -0.07
    award
    -0.07
    ё
    -0.07
    better
    -0.06
    елич
    -0.06
     abolished
    -0.06
    otic
    -0.06
    POSITIVE LOGITS
     αξ
    0.07
     isEnabled
    0.07
     tươi
    0.06
    $$$$
    0.06
     testim
    0.06
     kıl
    0.06
    美元
    0.06
    .Sqrt
    0.06
    推薦
    0.06
     spreads
    0.06
    Act Density 0.011%

    No Known Activations