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

    Neuronpedia

    INDEX
    Explanations

    topics and interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    也
    0.61
     também
    0.56
    ，
    0.51
     juga
    0.50
    ك
    0.50
     have
    0.48
      
    0.47
     també
    0.46
     also
    0.45
     भी
    0.45
    POSITIVE LOGITS
     дож
    0.44
     pédicule
    0.44
     montagnes
    0.43
     дату
    0.43
     کوي
    0.42
     эл
    0.42
     professionnelle
    0.41
     આં
    0.41
    +](=
    0.41
    ኞች
    0.40
    Act Density 0.002%

    No Known Activations