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

    Neuronpedia

    INDEX
    Explanations

    reason or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     your
    0.66
     dodgy
    0.55
     this
    0.53
     dirty
    0.50
    your
    0.49
     a
    0.49
     trying
    0.49
     votre
    0.49
     the
    0.47
     yourself
    0.47
    POSITIVE LOGITS
     Потому
    0.69
     زیرا
    0.67
    because
    0.66
     ponieważ
    0.66
    因为它
    0.66
    Because
    0.64
     Çünkü
    0.64
     ஏனெனில்
    0.64
     Bởi
    0.64
     Because
    0.64
    Act Density 0.003%

    No Known Activations