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

    Neuronpedia

    INDEX
    Explanations

    writing and communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ത്തിയാ
    0.46
     twinkling
    0.42
     영상을
    0.42
     invis
    0.40
     wink
    0.40
     televised
    0.40
     proteins
    0.40
     cá
    0.39
     electrons
    0.39
     linger
    0.39
    POSITIVE LOGITS
    生態
    0.55
    ב
    0.49
    成長
    0.45
    Все
    0.45
    வோ
    0.45
    葉
    0.44
    สัย
    0.43
    Acid
    0.43
    ämän
    0.43
    浅
    0.42
    Act Density 0.000%

    No Known Activations