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

    Neuronpedia

    INDEX
    Explanations

    の

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beet
    -0.07
     Lucifer
    -0.07
     hebben
    -0.07
     yet
    -0.07
    \Validator
    -0.07
    eller
    -0.07
     обычно
    -0.06
     FLT
    -0.06
     داده
    -0.06
    tering
    -0.06
    POSITIVE LOGITS
    84
    0.07
    子の
    0.07
    、この
    0.07
     onların
    0.07
    ンの
    0.07
    스의
    0.07
    の
    0.07
     of
    0.06
    	of
    0.06
    优
    0.06
    Act Density 0.012%

    No Known Activations