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

    Neuronpedia

    INDEX
    Explanations

    moving into or through places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Coming
    0.21
    oy
    0.20
     estuv
    0.19
    ₁+
    0.19
    Going
    0.19
     Gdy
    0.19
     terletak
    0.19
     estando
    0.19
    Staying
    0.19
     avec
    0.18
    POSITIVE LOGITS
     into
    0.74
    into
    0.56
     इनटू
    0.54
     vào
    0.53
     INTO
    0.50
     onto
    0.48
     Into
    0.47
    Into
    0.46
     away
    0.44
     through
    0.43
    Act Density 0.169%

    No Known Activations