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

    Neuronpedia

    INDEX
    Explanations

    past experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subunits
    0.45
     budgeted
    0.44
    ల్లో
    0.42
     গাঁ
    0.41
    bilder
    0.40
     deliverables
    0.40
    鎊
    0.40
     Takeuchi
    0.39
    상이
    0.39
    OC
    0.39
    POSITIVE LOGITS
    Само
    0.49
    Эти
    0.49
    Г
    0.49
     উ
    0.48
    Если
    0.48
    Де
    0.47
    Источник
    0.47
    දිය
    0.46
    Анд
    0.46
    elize
    0.45
    Act Density 0.000%

    No Known Activations