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

    Neuronpedia

    INDEX
    Explanations

    verb followed by into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     фараз
    0.80
    राबरी
    0.78
     ہاں
    0.72
    ことがある
    0.70
    olius
    0.70
     abbia
    0.69
     മുഖ്യമ
    0.68
     থাকিলে
    0.67
    സിന്
    0.66
    కోండి
    0.65
    POSITIVE LOGITS
     into
    6.23
    into
    5.30
    Into
    5.06
     Into
    5.06
     INTO
    4.52
     vào
    4.28
     इनटू
    4.18
     onto
    3.33
     Vào
    2.53
     nto
    2.48
    Act Density 0.499%

    No Known Activations