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

    Neuronpedia

    INDEX
    Explanations

    of your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     negócios
    0.33
    รายละเอียด
    0.33
     Having
    0.32
    経済
    0.32
    having
    0.31
     ثلاثة
    0.31
     teniendo
    0.30
    পানি
    0.30
     giorni
    0.29
    Seeing
    0.29
    POSITIVE LOGITS
     each
    0.76
     the
    0.61
     your
    0.59
    each
    0.55
    每个
    0.52
    Each
    0.51
     EACH
    0.49
     mỗi
    0.48
     प्रत्येक
    0.46
     각
    0.44
    Act Density 0.124%

    No Known Activations