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

    Neuronpedia

    INDEX
    Explanations

    you just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الآن
    0.59
     frequentemente
    0.55
     now
    0.53
    potentially
    0.52
     ahora
    0.52
     désormais
    0.52
     nyní
    0.52
     Often
    0.51
    now
    0.50
     Now
    0.50
    POSITIVE LOGITS
    就会
    0.45
     просто
    0.45
    يكون
    0.45
     يكون
    0.42
    fections
    0.42
    くなります
    0.41
     might
    0.41
     بيكون
    0.40
     मलाइका
    0.40
    จะมี
    0.40
    Act Density 0.016%

    No Known Activations