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

    Neuronpedia

    INDEX
    Explanations

    seed, GPA, or GPU

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lar
    1.55
    dı
    1.48
    liance
    1.48
    us
    1.44
    ні
    1.44
    ์
    1.43
    ет
    1.41
    ド
    1.38
    ből
    1.38
    it
    1.37
    POSITIVE LOGITS
    1.65
     birdies
    1.41
     primo
    1.39
     baskets
    1.34
     capita
    1.28
     berths
    1.25
     suitcases
    1.25
    abouts
    1.24
     платфор
    1.23
     clubs
    1.22
    Act Density 0.001%

    No Known Activations