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

    Neuronpedia

    INDEX
    Explanations

    and or other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.73
    ?
    0.57
    .
    0.55
    ;
    0.55
    ()
    0.53
     này
    0.52
    </a>
    0.52
    0.52
    й
    0.52
    (
    0.52
    POSITIVE LOGITS
     whatnot
    0.82
     sebagainya
    0.81
    အတူ
    0.63
     অন্যান্য
    0.59
     ఇతర
    0.54
    នៅលើ
    0.53
    ंगाबाद
    0.52
     त्यामुळे
    0.51
     ተጨማሪ
    0.51
     ተመሳሳይ
    0.51
    Act Density 0.069%

    No Known Activations