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

    Neuronpedia

    INDEX
    Explanations

    measures time durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     blueberries
    0.38
     Nếu
    0.38
     sulfur
    0.36
     compressors
    0.36
     az
    0.36
     waffles
    0.36
     high
    0.34
     vapor
    0.34
     aluminum
    0.34
     triangles
    0.34
    POSITIVE LOGITS
    ani
    0.35
    ância
    0.35
    และการ
    0.35
    щение
    0.35
    azia
    0.34
    iranje
    0.34
    èse
    0.33
    écie
    0.33
    וד
    0.33
    름
    0.33
    Act Density 0.141%

    No Known Activations