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

    Neuronpedia

    INDEX
    Explanations

    Code/Data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Attr
    -0.07
     factions
    -0.07
     léka
    -0.06
     всіх
    -0.06
    Corp
    -0.06
     ance
    -0.06
     caucus
    -0.06
     supers
    -0.06
     Atkins
    -0.06
    GBP
    -0.06
    POSITIVE LOGITS
    !)↵↵
    0.07
    ated
    0.07
    olume
    0.07
    ,copy
    0.06
     systematically
    0.06
     parachute
    0.06
     Public
    0.06
    وجد
    0.06
     очевид
    0.06
    _example
    0.06
    Act Density 0.000%

    No Known Activations