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

    Neuronpedia

    INDEX
    Explanations

    academic semesters and quarters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لیګ
    0.78
    یم
    0.69
    یت
    0.69
    ب
    0.65
    す
    0.65
    на
    0.64
    ו
    0.64
    המ
    0.62
    спубли
    0.61
    و
    0.61
    POSITIVE LOGITS
    ed
    0.67
     semester
    0.66
     сре
    0.64
     soud
    0.61
    ka
    0.61
    唵
    0.61
    AR
    0.60
    OA
    0.60
     Amsterdam
    0.58
     aant
    0.58
    Act Density 0.001%

    No Known Activations