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

    Neuronpedia

    INDEX
    Explanations

    prep time duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    name
    0.50
     okol
    0.43
     noyau
    0.41
    േഷന്‍
    0.40
    pflege
    0.40
    hostname
    0.39
    ^*\
    0.38
    Amerika
    0.38
    Utah
    0.38
    atini
    0.38
    POSITIVE LOGITS
     PDF
    0.50
     Embed
    0.44
     Academic
    0.41
     Rating
    0.41
    вена
    0.41
     downloads
    0.40
     Downloading
    0.40
     JSTOR
    0.40
     लेना
    0.39
     Sharma
    0.39
    Act Density 0.001%

    No Known Activations