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

    Neuronpedia

    INDEX
    Explanations

    fees and subscriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fur
    0.43
    Fur
    0.41
     exos
    0.39
     Fourier
    0.38
     Sparse
    0.38
     neur
    0.37
    Cuánt
    0.37
     polarization
    0.37
    口味
    0.37
     Poincaré
    0.36
    POSITIVE LOGITS
     fees
    3.23
     fee
    3.08
     Fees
    2.84
    Fees
    2.75
    fees
    2.72
     Fee
    2.63
    fee
    2.56
    Fee
    2.56
     फीस
    2.34
     FEES
    2.31
    Act Density 0.083%

    No Known Activations