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

    Neuronpedia

    INDEX
    Explanations

    huge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न
    2.27
    きた
    2.22
    ных
    2.20
    된
    2.19
    िक
    2.11
    ни
    2.03
    нови
    2.02
    ların
    1.99
    ❽
    1.99
    셸
    1.91
    POSITIVE LOGITS
    ó
    2.09
     وعلى
    1.92
    şti
    1.73
    PEND
    1.71
    ש
    1.69
    да
    1.68
    onter
    1.67
    yard
    1.66
    ्ले
    1.64
    ED
    1.63
    Act Density 0.013%

    No Known Activations