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

    Neuronpedia

    INDEX
    Explanations

    quantities and scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     এবং
    0.50
     и
    0.46
     आणि
    0.45
    했고
    0.41
     và
    0.40
     και
    0.39
     और
    0.38
     şi
    0.38
     and
    0.38
    wherein
    0.37
    POSITIVE LOGITS
     стрем
    0.41
    বিজ্ঞান
    0.40
    רוב
    0.39
     ټول
    0.39
     Be
    0.38
     Consid
    0.38
     учены
    0.38
     Бе
    0.37
     Consider
    0.37
     Informed
    0.37
    Act Density 0.000%

    No Known Activations