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

    Neuronpedia

    INDEX
    Explanations

    how much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tantas
    0.47
    ములు
    0.42
     للمعارف
    0.41
    菄
    0.41
     अजी
    0.40
     ලද
    0.40
     thereupon
    0.40
     Wesleyan
    0.38
    खाव
    0.38
    olics
    0.38
    POSITIVE LOGITS
    Quanto
    0.99
     Quanto
    0.95
     quanto
    0.93
    quanto
    0.84
     cuanto
    0.72
    เท่า
    0.68
    Cuánto
    0.65
    いく
    0.61
     cât
    0.61
    หร่
    0.60
    Act Density 0.003%

    No Known Activations