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

    Neuronpedia

    INDEX
    Explanations

    ongoing action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     your
    0.74
     iyo
    0.59
     sağlar
    0.59
     vaše
    0.56
     sağlan
    0.56
     bạn
    0.56
     the
    0.54
     both
    0.54
     easily
    0.53
     temperate
    0.53
    POSITIVE LOGITS
     Están
    0.94
     estão
    0.82
     sedang
    0.82
    正在
    0.77
     đang
    0.76
     করছেন
    0.76
     করছে
    0.75
    をしている
    0.74
    presumably
    0.73
    apparently
    0.73
    Act Density 0.010%

    No Known Activations