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

    Neuronpedia

    INDEX
    Explanations

    definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    issing
    -0.06
    Jones
    -0.06
     cla
    -0.06
     spanking
    -0.06
     iframe
    -0.06
     squeezed
    -0.06
     Aunt
    -0.06
    ối
    -0.06
     migraine
    -0.06
    allele
    -0.06
    POSITIVE LOGITS
    .idx
    0.06
    RSA
    0.06
     где
    0.06
     Indeed
    0.06
    }{↵
    0.06
    environment
    0.06
     مرتب
    0.06
    \DependencyInjection
    0.06
     simplified
    0.06
    acic
    0.06
    Act Density 0.043%

    No Known Activations