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

    Neuronpedia

    INDEX
    Explanations

    capturing form or structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     debtor
    0.52
     to
    0.50
     ア
    0.48
    to
    0.48
     pharmacy
    0.47
     Performing
    0.47
     bookstore
    0.46
     simile
    0.46
    যানী
    0.45
     doctorate
    0.45
    POSITIVE LOGITS
    ڙ
    0.46
    情報の
    0.44
     aparent
    0.43
    赟
    0.43
    鷸
    0.43
    дени
    0.42
     уника
    0.41
     Hv
    0.41
    薷
    0.41
    жет
    0.41
    Act Density 0.000%

    No Known Activations