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

    Neuronpedia

    INDEX
    Explanations

    specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发育
    -1.12
    tamientos
    -1.02
    麻辣
    -1.02
     Kig
    -1.02
    ┤
    -1.00
    polish
    -0.99
    膵
    -0.98
    edoria
    -0.97
    ⫻
    -0.97
     tiek
    -0.96
    POSITIVE LOGITS
     these
    1.27
    Também
    1.24
    或者
    1.23
    这些
    1.22
     потому
    1.19
    而
    1.19
     этих
    1.18
    いただきたい
    1.15
    But
    1.13
    Appellee
    1.12
    Act Density 0.055%

    No Known Activations