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

    Neuronpedia

    INDEX
    Explanations

    go to / reaches into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दर्शा
    0.60
     काफी
    0.59
    สามารถ
    0.55
     значительно
    0.55
    많
    0.55
     قابل
    0.54
     znacznie
    0.54
    ตลอด
    0.53
     considers
    0.53
     बेहतरीन
    0.52
    POSITIVE LOGITS
     into
    0.99
     out
    0.79
     Into
    0.72
    into
    0.69
     onto
    0.67
     इनटू
    0.67
     up
    0.66
    Into
    0.66
     down
    0.66
     unto
    0.65
    Act Density 0.216%

    No Known Activations