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

    Neuronpedia

    INDEX
    Explanations

    systems of linear equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unteer
    1.10
     invariably
    1.09
     otomatis
    1.07
     komunitas
    1.07
     verticals
    1.06
    fortunately
    1.05
     prostitute
    1.04
     frantically
    1.03
     evacu
    1.03
     klub
    1.03
    POSITIVE LOGITS
     Google
    0.78
    翻
    0.75
     Aug
    0.75
     w
    0.73
     Tennessee
    0.69
     ا
    0.68
     கெ
    0.68
     Core
    0.67
     सू
    0.67
     Gute
    0.66
    Act Density 0.001%

    No Known Activations