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

    Neuronpedia

    INDEX
    Explanations

    lebesgue measure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rections
    -0.07
    웨
    -0.07
    ridden
    -0.06
    akest
    -0.06
     unlike
    -0.06
     Arth
    -0.06
    	ok
    -0.06
    노출
    -0.06
     Nightmare
    -0.06
     WAV
    -0.06
    POSITIVE LOGITS
     celebrity
    0.07
     μπορού
    0.06
    ©©
    0.06
     murdering
    0.06
     Obama
    0.06
    (util
    0.06
    CONST
    0.06
     오늘
    0.06
     mark
    0.06
     horribly
    0.06
    Act Density 0.003%

    No Known Activations