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

    Neuronpedia

    INDEX
    Explanations

    quality descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Benchmark
    0.43
    oszt
    0.41
     ቀለም
    0.39
     цвета
    0.38
     nominate
    0.38
    Output
    0.37
     કા
    0.36
     сход
    0.36
    material
    0.35
    Color
    0.35
    POSITIVE LOGITS
     pan
    0.43
     thigh
    0.42
     pans
    0.42
     thorac
    0.41
    ilets
    0.40
     toilet
    0.39
     potty
    0.39
    ﮄ
    0.39
    pertensive
    0.39
     pant
    0.38
    Act Density 0.005%

    No Known Activations