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

    Neuronpedia

    INDEX
    Explanations

    kinds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	My
    -0.07
    $mail
    -0.07
     розум
    -0.07
    	dist
    -0.06
     Ori
    -0.06
    -ins
    -0.06
    	us
    -0.06
    .photos
    -0.06
    測
    -0.06
     Kop
    -0.06
    POSITIVE LOGITS
     условиях
    0.07
    “They
    0.07
     této
    0.07
     tomto
    0.07
    ergisi
    0.06
    我们
    0.06
     Germany
    0.06
    물을
    0.06
    ้ไข
    0.06
     jejich
    0.06
    Act Density 0.102%

    No Known Activations