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

    Neuronpedia

    INDEX
    Explanations

    adding or extending features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Alguns
    0.72
     които
    0.66
     MODKEY
    0.66
     misfortunes
    0.65
    左右
    0.65
     някои
    0.64
     niektó
    0.64
     których
    0.64
     многих
    0.64
     kiuj
    0.63
    POSITIVE LOGITS
     interactive
    0.86
     also
    0.78
     extensible
    0.76
     flexible
    0.75
     then
    0.71
     informative
    0.70
     filled
    0.70
     attached
    0.70
     reusable
    0.70
     accompanied
    0.69
    Act Density 0.000%

    No Known Activations