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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'im
    -0.07
     Απ
    -0.06
    -operator
    -0.06
    мещ
    -0.06
    령
    -0.06
    ozem
    -0.06
     sab
    -0.06
     ring
    -0.06
     Amerikan
    -0.06
     OEM
    -0.06
    POSITIVE LOGITS
     institute
    0.07
    　　 　 　 　 　
    0.06
     diện
    0.06
     categoryId
    0.06
    하기
    0.06
    rouch
    0.06
     synth
    0.06
     pylint
    0.06
    		↵	↵
    0.05
    .assertIsNot
    0.05
    Act Density 0.000%

    No Known Activations