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

    Neuronpedia

    INDEX
    Explanations

    possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ру
    0.51
    ráf
    0.51
    ат
    0.50
    propTypes
    0.49
    axes
    0.48
    не
    0.48
    assets
    0.48
    problem
    0.48
    рата
    0.47
    ỡng
    0.47
    POSITIVE LOGITS
    的可能性
    0.62
     possibility
    0.61
     posibilidad
    0.57
     POSSIBILITY
    0.55
     mahdoll
    0.54
     scenario
    0.50
     Poss
    0.50
     teore
    0.49
     możliwość
    0.49
     poss
    0.49
    Act Density 0.013%

    No Known Activations