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

    Neuronpedia

    INDEX
    Explanations

    thousands of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ς
    1.21
    s
    1.13
     ribu
    1.13
     রকমের
    1.11
    钅
    1.03
    կ
    1.02
    ડ
    0.98
     automó
    0.94
    ข้อง
    0.93
    ség
    0.93
    POSITIVE LOGITS
    ী
    1.09
    ed
    1.02
    ized
    1.00
    ित
    0.98
     revitalize
    0.97
     Responsive
    0.90
    न
    0.90
    ン
    0.89
    ess
    0.88
    ی
    0.88
    Act Density 0.000%

    No Known Activations