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

    Neuronpedia

    INDEX
    Explanations

    factory farms and animal welfare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    宁
    -0.07
     Bil
    -0.07
    ,:,
    -0.07
    Om
    -0.07
    析
    -0.06
    벨
    -0.06
    яем
    -0.06
    Independ
    -0.06
     {
    -0.06
    Mot
    -0.06
    POSITIVE LOGITS
     foundational
    0.07
    medi
    0.07
     adjustments
    0.06
     Blast
    0.06
    (MethodImplOptions
    0.06
     entreprise
    0.06
    iationException
    0.06
     insecure
    0.06
     medi
    0.06
     ARISING
    0.06
    Act Density 0.042%

    No Known Activations