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

    Neuronpedia

    INDEX
    Explanations

    for i in range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Another
    0.69
    arynx
    0.68
     चतुर्थ
    0.68
    Another
    0.67
     geç
    0.67
    带宽
    0.66
     എന്ന്
    0.64
     रणनी
    0.64
    фона
    0.62
    fullscreen
    0.62
    POSITIVE LOGITS
     sorted
    2.08
     list
    1.99
    sorted
    1.91
    list
    1.73
    Sorted
    1.50
     Sorted
    1.46
     [*
    1.44
    [*
    1.39
    zip
    1.39
     range
    1.38
    Act Density 0.198%

    No Known Activations