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

    Neuronpedia

    INDEX
    Explanations

    timing and positive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ؛
    0.52
                   
    0.46
     प्रस्तुत
    0.46
     Repert
    0.46
     Computational
    0.45
     Bharati
    0.44
    🏛
    0.44
    ・
    0.44
     மூன்று
    0.44
     және
    0.44
    POSITIVE LOGITS
     lvl
    0.56
     devs
    0.55
     ammo
    0.49
     enduro
    0.49
     ssd
    0.46
     camo
    0.45
     decently
    0.45
     bbq
    0.45
     xmas
    0.44
     veggies
    0.43
    Act Density 0.008%

    No Known Activations