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

    Neuronpedia

    INDEX
    Explanations

    do not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sidelined
    0.43
     unsurprisingly
    0.42
     policymakers
    0.42
     outfitted
    0.42
    नेश्वर
    0.41
     uptick
    0.40
     embroiled
    0.39
     comedic
    0.39
     telecoms
    0.39
     shockingly
    0.39
    POSITIVE LOGITS
     v
    0.45
     "
    0.41
     g
    0.40
     b
    0.39
     t
    0.39
       
    0.38
     n
    0.38
     s
    0.38
    P
    0.37
     l
    0.37
    Act Density 0.039%

    No Known Activations