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

    Neuronpedia

    INDEX
    Explanations

    into, with, together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Saut
    0.42
    ಸೂ
    0.41
     Walls
    0.40
     Yash
    0.39
     sucking
    0.38
     wading
    0.38
     Les
    0.38
     Flights
    0.38
     সত্ত
    0.38
     Hesse
    0.37
    POSITIVE LOGITS
     awake
    0.68
     into
    0.67
    into
    0.64
     down
    0.58
     вниз
    0.53
     lên
    0.52
     together
    0.50
    awake
    0.50
    Into
    0.50
    together
    0.49
    Act Density 0.014%

    No Known Activations