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

    Neuronpedia

    INDEX
    Explanations

    of course

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্রে
    2.05
    ४
    2.04
    ﯼ
    1.97
    SOD
    1.90
     tiz
    1.88
    ิบ
    1.88
    czny
    1.88
    otesi
    1.85
    लिसा
    1.83
     comboBox
    1.83
    POSITIVE LOGITS
    м
    3.02
    кти
    2.31
     treba
    2.28
    年
    2.24
    ку
    2.20
    ാ
    2.06
    ine
    2.06
     amply
    2.06
    ll
    2.03
     oczy
    1.99
    Act Density 0.016%

    No Known Activations