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

    Neuronpedia

    INDEX
    Explanations

    what kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cer
    0.38
    )(
    0.38
    罪
    0.37
    ெ
    0.36
    otal
    0.35
    met
    0.35
    EMT
    0.35
     cul
    0.34
    対
    0.34
     ruling
    0.34
    POSITIVE LOGITS
    operatively
    0.53
     Hamburg
    0.49
    ਕਾਰੀ
    0.47
     Tweets
    0.45
     Хоккей
    0.44
     சென்னையில்
    0.44
     Customer
    0.44
     කරන්න
    0.44
     কমলনগর
    0.44
     Yokohama
    0.44
    Act Density 0.002%

    No Known Activations