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

    Neuronpedia

    INDEX
    Explanations

    packed, brimming, filled with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     используя
    0.74
    чего
    0.72
    并在
    0.70
    નના
    0.69
    право
    0.68
    放到
    0.66
    tis
    0.65
    ത്തിനെ
    0.64
     באמצעות
    0.63
    പടി
    0.63
    POSITIVE LOGITS
     brimming
    1.13
     riddled
    1.11
     filled
    1.08
    ไปด้วย
    1.05
     lleno
    1.01
     with
    1.00
    filled
    0.99
     beset
    0.95
     laced
    0.93
     dengan
    0.93
    Act Density 0.111%

    No Known Activations