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

    Neuronpedia

    INDEX
    Explanations

    certain specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     همچنین
    0.40
    မ္
    0.39
    both
    0.38
     және
    0.36
     للنساء
    0.36
    両
    0.36
     பேச்சு
    0.35
     അത്
    0.35
    crocodile
    0.35
    methylation
    0.34
    POSITIVE LOGITS
    某个
    1.24
     certain
    1.20
     특정
    1.12
    某些
    1.11
    某一
    1.07
     tertentu
    1.06
     bestimmte
    1.06
     bepaalde
    1.02
     bestimmten
    1.01
     particular
    0.98
    Act Density 0.669%

    No Known Activations