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

    Neuronpedia

    INDEX
    Explanations

    Names of people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     examples
    -0.07
     essence
    -0.07
     democr
    -0.06
    ramer
    -0.06
    .Test
    -0.06
     obscure
    -0.06
     Kü
    -0.06
     neuroscience
    -0.06
    星
    -0.06
    though
    -0.06
    POSITIVE LOGITS
     شما
    0.07
     جل
    0.07
     يا
    0.06
    userInfo
    0.06
     longitud
    0.06
     بنا
    0.06
     freelancer
    0.06
    ليم
    0.06
     binnen
    0.06
     MMI
    0.06
    Act Density 0.009%

    No Known Activations