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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	spec
    -0.07
    าษ
    -0.06
     IX
    -0.06
     RD
    -0.06
     monstrous
    -0.06
    털
    -0.06
    πι
    -0.06
    Expires
    -0.06
    Could
    -0.06
    ，有
    -0.06
    POSITIVE LOGITS
     аг
    0.09
    <b
    0.08
    ajes
    0.07
     conect
    0.07
     kurs
    0.07
    metro
    0.07
    =back
    0.07
     agreg
    0.07
    ник
    0.07
     estar
    0.06
    Act Density 0.651%

    No Known Activations