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

    Neuronpedia

    INDEX
    Explanations

    function return values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ма
    2.28
     När
    2.25
    kwargs
    2.12
     proprement
    2.11
    於
    2.10
    pt
    2.08
    િલે
    2.03
    ítás
    2.03
     dej
    1.99
    ından
    1.98
    POSITIVE LOGITS
     LOTRAchievement
    2.74
     BuildConfig
    2.60
    eau
    2.48
    ر
    2.44
    ν
    2.43
    ن
    2.42
    nement
    2.42
    ture
    2.42
    νε
    2.40
    sprite
    2.38
    Act Density 0.089%

    No Known Activations