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

    Neuronpedia

    INDEX
    Explanations

    future outlook and projections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     টিকে
    0.56
    pley
    0.56
    ம்தா
    0.55
    ਿਲ
    0.55
    Trains
    0.55
     resear
    0.54
    ัต
    0.54
     Elapsed
    0.54
     elef
    0.53
    ﮑ
    0.53
    POSITIVE LOGITS
    젠
    0.59
    間で
    0.58
     dough
    0.55
     ско
    0.55
    acker
    0.54
     الخير
    0.53
    머니
    0.53
     मिळाले
    0.52
     comentarios
    0.52
     be
    0.52
    Act Density 0.001%

    No Known Activations