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

    Neuronpedia

    INDEX
    Explanations

    TL, TLB, tl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desa
    0.81
     Herbert
    0.73
     return
    0.73
     Girl
    0.72
     Patient
    0.71
     ইহ
    0.71
     मार्केटिंग
    0.70
     첫
    0.70
     Harriet
    0.70
    ชม
    0.70
    POSITIVE LOGITS
    TL
    1.56
     TL
    1.47
    tl
    1.03
    Tl
    0.97
     HL
    0.86
    DL
    0.85
     TLR
    0.84
     AML
    0.84
     DL
    0.83
    ML
    0.83
    Act Density 0.000%

    No Known Activations