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

    Neuronpedia

    INDEX
    Explanations

    staff and employees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pamoja
    1.09
    ット
    1.03
     Accessed
    0.98
    ต้น
    0.96
     tambah
    0.93
     של
    0.93
    ซ์
    0.93
     Ones
    0.90
     seben
    0.90
    К
    0.89
    POSITIVE LOGITS
    ف
    1.12
    ס
    1.09
    ون
    1.08
    ان
    1.06
    StaffID
    1.06
    вата
    1.01
    ле
    1.00
    тал
    0.98
    ط
    0.98
    ی
    0.98
    Act Density 0.097%

    No Known Activations