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

    Neuronpedia

    INDEX
    Explanations

    relative, same, time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     här
    0.51
     aqui
    0.40
     tutaj
    0.40
     방식
    0.39
     here
    0.39
     bog
    0.38
    Sen
    0.38
     тут
    0.38
    ımıza
    0.38
    Dio
    0.37
    POSITIVE LOGITS
     unequiv
    0.43
     शर्तें
    0.42
     മെ
    0.41
    ições
    0.40
    untlet
    0.40
    <unused636>
    0.38
    timeInterval
    0.38
     unequivocally
    0.38
    เพื่อให้
    0.38
     জায়
    0.38
    Act Density 0.000%

    No Known Activations