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

    Neuronpedia

    INDEX
    Explanations

    no registration or ads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     symbiotic
    0.42
    imeric
    0.41
     defied
    0.39
     Society
    0.38
     pragmatic
    0.38
     লইয়া
    0.38
     திரி
    0.38
     admired
    0.37
     cate
    0.37
     pinn
    0.37
    POSITIVE LOGITS
     Required
    0.61
    Required
    0.61
     required
    0.59
    广告
    0.59
     ads
    0.59
     fees
    0.57
     mandatory
    0.57
    廣告
    0.57
    required
    0.56
     quảng
    0.55
    Act Density 0.016%

    No Known Activations