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

    Neuronpedia

    INDEX
    Explanations

    float and align

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Commentary
    0.45
     shank
    0.45
     dev
    0.44
    VL
    0.44
     VL
    0.43
     nuclear
    0.43
     Cer
    0.42
     racetrack
    0.42
     typeface
    0.42
    錨
    0.41
    POSITIVE LOGITS
     মুজিবের
    0.43
     പരി
    0.43
     सुने
    0.42
    bookings
    0.40
    ப்புகளை
    0.38
    itect
    0.38
     त्रुट
    0.37
     இருந்தது
    0.37
    诊
    0.37
    ඩ්
    0.36
    Act Density 0.000%

    No Known Activations