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

    Neuronpedia

    INDEX
    Explanations

    starts phrases or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     certificat
    0.51
     prévenir
    0.49
     sonra
    0.48
     그는
    0.47
     décoration
    0.46
     contienen
    0.46
     localisation
    0.45
     অভিনে
    0.44
    udarstven
    0.44
    fonction
    0.44
    POSITIVE LOGITS
    ン
    0.68
    th
    0.48
    តា
    0.47
    n
    0.47
    ina
    0.47
     Dina
    0.47
     Dividing
    0.46
    ul
    0.45
     Tans
    0.45
    ಮ
    0.44
    Act Density 0.012%

    No Known Activations