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

    Neuronpedia

    INDEX
    Explanations

    Entitlements/Rights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Flying
    -0.07
    .tables
    -0.07
    榜
    -0.06
    medicine
    -0.06
    flatten
    -0.06
    ParameterValue
    -0.06
    Technology
    -0.06
     멀
    -0.06
     транспорт
    -0.06
    Form
    -0.06
    POSITIVE LOGITS
     nedok
    0.07
     Гар
    0.07
    альну
    0.07
     brilliantly
    0.07
    uj
    0.07
     constantly
    0.07
     제가
    0.06
     جور
    0.06
     imposing
    0.06
     관심
    0.06
    Act Density 0.007%

    No Known Activations