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

    Neuronpedia

    INDEX
    Explanations

    geopolitical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     galerie
    0.43
     compares
    0.42
    たる
    0.40
     clarify
    0.40
     elucidate
    0.40
     proactively
    0.39
     clarifies
    0.39
     explore
    0.38
     revoke
    0.38
     impressively
    0.38
    POSITIVE LOGITS
     స్టే
    0.54
    ide
    0.53
    처럼
    0.53
     Boolean
    0.48
     государ
    0.48
    essa
    0.48
    iai
    0.48
     BufferedImage
    0.48
    ergic
    0.46
    hel
    0.45
    Act Density 0.011%

    No Known Activations