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

    Neuronpedia

    INDEX
    Explanations

    That

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    being
    1.73
     being
    1.72
    Being
    1.67
     Being
    1.40
    having
    1.37
     BEING
    1.32
    Having
    1.25
     sendo
    1.19
     having
    1.15
     fiind
    1.10
    POSITIVE LOGITS
     ถ้า
    0.86
     криптовалю
    0.83
    ’.
    0.75
    乜
    0.75
     perchè
    0.74
     शिवराज
    0.72
     ค่ะ
    0.71
     waxay
    0.71
     polypes
    0.70
     مصرى
    0.70
    Act Density 0.000%

    No Known Activations