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

    Neuronpedia

    INDEX
    Explanations

    they, can, Leo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perpetrator
    0.46
    ிலி
    0.46
    штейн
    0.43
     zombies
    0.42
    луйста
    0.42
    படுத்த
    0.41
     attualmente
    0.41
     utilisons
    0.41
     парк
    0.41
     vreau
    0.41
    POSITIVE LOGITS
    they
    0.66
     They
    0.65
    他们
    0.64
     他们
    0.64
    他們
    0.61
    They
    0.61
     they
    0.59
    their
    0.58
     their
    0.54
     তারা
    0.54
    Act Density 0.061%

    No Known Activations