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

    Neuronpedia

    INDEX
    Explanations

    contracts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trucking
    0.53
     lucrative
    0.52
     susp
    0.50
     seven
    0.50
     nombreux
    0.49
     hydropon
    0.49
     افس
    0.49
     tats
    0.49
     cette
    0.49
     многочис
    0.48
    POSITIVE LOGITS
    im
    0.65
    n
    0.64
    il
    0.64
    i
    0.64
    os
    0.63
    ut
    0.63
    ot
    0.63
    O
    0.63
    t
    0.61
    us
    0.58
    Act Density 0.000%

    No Known Activations