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

    Neuronpedia

    INDEX
    Explanations

    offensive slurs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    megen
    0.39
     shelters
    0.39
     salicylate
    0.38
    μό
    0.37
     shelter
    0.36
    鏁
    0.36
     Legion
    0.36
     buildTypes
    0.36
    dam
    0.36
    ogaster
    0.36
    POSITIVE LOGITS
     जुगा
    0.42
     करुन
    0.41
     १४
    0.40
     Trol
    0.38
     Беларусі
    0.38
     Finn
    0.37
     Amazing
    0.37
     Expertise
    0.37
    ాడు
    0.36
    Adapter
    0.36
    Act Density 0.000%

    No Known Activations