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

    Neuronpedia

    INDEX
    Explanations

    lists of entities and their descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.59
    7
    0.48
    و
    0.48
    .
    0.41
    வ்வேறு
    0.40
    зульта
    0.40
    ﻔ
    0.38
    5
    0.38
    4
    0.38
    ता
    0.37
    POSITIVE LOGITS
     from
    0.75
     on
    0.63
     of
    0.59
     with
    0.57
     at
    0.53
    k
    0.52
     out
    0.48
     to
    0.46
    r
    0.45
    n
    0.44
    Act Density 1.967%

    No Known Activations