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

    Neuronpedia

    INDEX
    Explanations

    proving something to be true

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transacción
    0.45
     ฝึก
    0.44
     Transactions
    0.43
    transactions
    0.43
    likelihood
    0.40
     transactions
    0.40
    离开了
    0.38
     거래
    0.38
     Makes
    0.38
     Achievement
    0.37
    POSITIVE LOGITS
     prove
    0.75
     proved
    0.72
     proving
    0.67
     proves
    0.66
     elusive
    0.62
    proved
    0.56
     být
    0.55
     resilient
    0.55
     साबित
    0.54
    证明
    0.54
    Act Density 0.002%

    No Known Activations