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

    Neuronpedia

    INDEX
    Explanations

    the `token`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ammation
    0.43
     elders
    0.43
    ighting
    0.42
    oth
    0.41
     palpitations
    0.40
    mack
    0.38
    к
    0.38
    Mods
    0.38
     getServer
    0.38
     keepers
    0.37
    POSITIVE LOGITS
     प्रिज्म
    0.48
    بە
    0.42
     १८४
    0.41
     عادة
    0.41
    າດ
    0.40
     ilegal
    0.40
    때
    0.40
     प्रावधान
    0.39
    🏺
    0.39
     işaret
    0.39
    Act Density 0.002%

    No Known Activations