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

    Neuronpedia

    INDEX
    Explanations

    being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    руя
    0.42
    тых
    0.41
    把
    0.41
    ிகளை
    0.40
    ಿತ್ತು
    0.39
    ruire
    0.39
     Dorsey
    0.39
     झटका
    0.38
    ິກ
    0.38
    可以将
    0.38
    POSITIVE LOGITS
     being
    0.84
    被
    0.79
    being
    0.78
    Being
    0.77
     Being
    0.74
     להיות
    0.73
     membuatnya
    0.72
     BEING
    0.71
     bị
    0.69
    使其
    0.67
    Act Density 0.029%

    No Known Activations