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

    Neuronpedia

    INDEX
    Explanations

    startup folders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cauliflower
    0.47
     potash
    0.44
     applicator
    0.41
     limes
    0.41
     mastectomy
    0.40
     rhubarb
    0.40
     isomerization
    0.40
     gingham
    0.40
    塗装
    0.39
     lemongrass
    0.39
    POSITIVE LOGITS
    Download
    0.47
    simple
    0.44
     Download
    0.43
    Simple
    0.42
    DOWNLOAD
    0.40
    we
    0.39
    Pdf
    0.39
    download
    0.38
     Kindle
    0.38
     Lesen
    0.38
    Act Density 0.000%

    No Known Activations