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

    Neuronpedia

    INDEX
    Explanations

    finding hidden places and reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اؤ
    0.58
    Meeting
    0.48
    You
    0.46
    Malay
    0.46
    Se
    0.46
    Jazz
    0.45
    Reading
    0.45
    Situ
    0.44
    Maritime
    0.44
    Atm
    0.43
    POSITIVE LOGITS
     intimidating
    0.52
     voisins
    0.48
     pim
    0.48
     associa
    0.48
     ranchers
    0.47
     lovingly
    0.46
     আসবেন
    0.46
     procurando
    0.46
     pum
    0.46
    पिक्सल
    0.45
    Act Density 0.001%

    No Known Activations