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

    Neuronpedia

    INDEX
    Explanations

    command structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मुख्‍य
    0.35
    및
    0.35
     наших
    0.34
    的主要
    0.33
     ఎక్కువగా
    0.33
    <unused236>
    0.33
     ہمارے
    0.32
     вашего
    0.32
    客様
    0.32
    <unused709>
    0.32
    POSITIVE LOGITS
     it
    0.32
     I
    0.31
     lensing
    0.29
    clip
    0.29
     accomplishing
    0.29
    0.29
     =
    0.28
     clip
    0.28
     Corner
    0.28
     receptor
    0.28
    Act Density 0.115%

    No Known Activations