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

    Neuronpedia

    INDEX
    Explanations

    look forward to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Forward
    0.62
    Forward
    0.59
    Foreground
    0.58
     Foreground
    0.56
     Front
    0.55
     Forecast
    0.50
     Frontend
    0.50
     foreground
    0.49
     Forecasting
    0.49
    forward
    0.49
    POSITIVE LOGITS
     look
    0.52
    look
    0.52
    Look
    0.51
     fram
    0.46
     اهلا
    0.43
    LOOK
    0.43
    akoti
    0.40
     පිළිබ
    0.39
    fram
    0.39
     bardzo
    0.39
    Act Density 0.002%

    No Known Activations