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

    Neuronpedia

    INDEX
    Explanations

    giving advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Use
    0.43
     use
    0.40
     same
    0.39
     utilisez
    0.38
    big
    0.38
     Through
    0.38
    还是
    0.37
    7
    0.37
     Where
    0.37
     Due
    0.37
    POSITIVE LOGITS
    使得
    0.46
     ervoor
    0.44
     them
    0.43
     negotiators
    0.40
     credence
    0.39
     impetus
    0.39
     concomit
    0.38
    tabPadding
    0.38
     మరింత
    0.38
    িলো
    0.38
    Act Density 0.017%

    No Known Activations