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

    Neuronpedia

    INDEX
    Explanations

    average

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متش
    0.44
     Polyester
    0.40
     Chromium
    0.40
     bevor
    0.39
     inventories
    0.38
     sumar
    0.38
     Measurement
    0.38
     গের
    0.37
     wrinkled
    0.37
     Pathways
    0.37
    POSITIVE LOGITS
    平均
    1.02
     average
    0.93
    average
    0.92
     averaged
    0.84
     durchschnitt
    0.82
    Average
    0.80
     averaging
    0.80
     averages
    0.78
     AVERAGE
    0.77
     平均
    0.75
    Act Density 0.086%

    No Known Activations