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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ang
    0.40
    ờ
    0.40
    Ét
    0.39
    Secondo
    0.39
    uder
    0.38
    Bag
    0.38
     potom
    0.38
    ¹)
    0.38
    Beg
    0.38
     பச
    0.38
    POSITIVE LOGITS
     frequency
    0.40
    iphy
    0.38
     Arbitration
    0.38
     shocks
    0.37
    ضغط
    0.37
     कक्ष
    0.37
     الفاظ
    0.37
    frequency
    0.36
     सेल्स
    0.36
     securities
    0.36
    Act Density 0.003%

    No Known Activations