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

    Neuronpedia

    INDEX
    Explanations

    enough to warrant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    มากขึ้น
    1.33
    1.11
    minded
    1.07
    ক
    1.03
    使用的是
    1.02
    hive
    1.00
    更多
    0.97
    IS
    0.96
    ようになりました
    0.94
     davantage
    0.93
    POSITIVE LOGITS
     warrant
    1.22
     warrants
    1.05
     Apparently
    0.96
     bekannt
    0.96
    selves
    0.93
     firepower
    0.91
    면
    0.91
    ೂರ
    0.89
     kendini
    0.89
    isticated
    0.87
    Act Density 0.046%

    No Known Activations