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

    Neuronpedia

    INDEX
    Explanations

    according to sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wondered
    0.79
     asks
    0.77
     considerados
    0.72
     chiede
    0.70
    breaker
    0.69
    piece
    0.68
    azgo
    0.67
     or
    0.66
     혹은
    0.66
     respectiv
    0.65
    POSITIVE LOGITS
    目前的
    1.22
     our
    1.05
     recent
    0.99
     experts
    0.98
     their
    0.97
     מיט
    0.96
     специалистов
    0.94
    最新的
    0.94
     available
    0.93
     नवीनतम
    0.92
    Act Density 0.040%

    No Known Activations