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

    Neuronpedia

    INDEX
    Explanations

    different hemispheres or distinctive elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ５
    0.43
     प
    0.43
    ன்
    0.41
     ها
    0.41
    !(
    0.40
     लागि
    0.40
    いった
    0.40
    平成
    0.40
    ۶
    0.40
     অতঃপর
    0.40
    POSITIVE LOGITS
     omnichannel
    0.47
     meats
    0.44
     perish
    0.41
     perfeita
    0.40
     UICtrl
    0.40
     métiers
    0.40
    🥉
    0.40
    暉
    0.39
     perfetta
    0.39
     cards
    0.39
    Act Density 0.003%

    No Known Activations