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

    Neuronpedia

    INDEX
    Explanations

    non-English words and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thoughts
    0.45
    Thoughts
    0.42
     Collision
    0.41
    ه
    0.41
    Y
    0.41
    Ü
    0.41
    BB
    0.41
    c
    0.40
    에
    0.40
    RE
    0.40
    POSITIVE LOGITS
     Paryayvachi
    0.57
     shabd
    0.54
    ಓ
    0.49
     ആശുപത്രി
    0.48
    iyar
    0.48
     Panchayat
    0.47
     mirip
    0.47
     পরিষ
    0.47
     nyní
    0.46
    癹
    0.46
    Act Density 0.000%

    No Known Activations