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

    Neuronpedia

    INDEX
    Explanations

    Taylor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uppies
    -0.07
     по
    -0.06
    Ε
    -0.06
    ='#
    -0.06
    en
    -0.06
     Е
    -0.06
     mounting
    -0.06
     ske
    -0.06
    續
    -0.06
    notEmpty
    -0.06
    POSITIVE LOGITS
     Taylor
    0.12
    Taylor
    0.11
     pear
    0.09
     ayr
    0.08
    ตล
    0.08
     पर
    0.08
    dfa
    0.08
     berry
    0.07
     UserProfile
    0.07
     Sears
    0.07
    Act Density 0.003%

    No Known Activations