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

    Neuronpedia

    INDEX
    Explanations

    pixel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    شم
    0.42
     acumin
    0.41
     Severity
    0.39
     VHF
    0.38
     Rhin
    0.38
     rozp
    0.37
     Interpret
    0.37
     remodeling
    0.37
     Frequency
    0.37
     decl
    0.36
    POSITIVE LOGITS
     pixel
    0.70
    pixel
    0.62
    Pixel
    0.62
     pixels
    0.60
    pixels
    0.55
     Pixel
    0.53
    像素
    0.52
    pix
    0.51
     pix
    0.49
    Pixels
    0.47
    Act Density 0.009%

    No Known Activations