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

    Neuronpedia

    INDEX
    Explanations

    into and onto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     После
    0.61
     ধারা
    0.60
    DFLAGS
    0.59
     रोचक
    0.58
    추
    0.58
    椀
    0.57
    のア
    0.57
    reszt
    0.56
    વાય
    0.56
    ေး
    0.55
    POSITIVE LOGITS
     onto
    3.33
     into
    3.32
    into
    2.81
    Into
    2.81
     Into
    2.77
     INTO
    2.50
     vào
    2.20
     इनटू
    2.11
     down
    2.09
    onto
    2.08
    Act Density 0.019%

    No Known Activations