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

    Neuronpedia

    INDEX
    Explanations

    dwell, double, break

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étant
    0.67
     cascades
    0.66
     and
    0.66
     grâce
    0.64
     which
    0.64
     engend
    0.63
     gastronomy
    0.63
     alcal
    0.62
     crée
    0.62
     océ
    0.62
    POSITIVE LOGITS
    Saldo
    0.64
    ン
    0.64
    n
    0.64
     jų
    0.62
    adple
    0.61
     информация
    0.60
     त्यांची
    0.60
    )}(\
    0.60
    siehe
    0.59
    ക്കുറിച്ച
    0.59
    Act Density 3.378%

    No Known Activations