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

    Neuronpedia

    INDEX
    Explanations

    bot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     watchers
    -0.07
    German
    -0.06
     �
    -0.06
     svůj
    -0.06
     Lua
    -0.06
    yna
    -0.06
    řik
    -0.06
     memes
    -0.06
     Pad
    -0.06
     NA
    -0.06
    POSITIVE LOGITS
    .self
    0.07
    (util
    0.07
    �
    0.06
    __':↵
    0.06
    رفته
    0.06
     detr
    0.06
    (gulp
    0.06
    ционного
    0.06
    _unlock
    0.06
     громад
    0.06
    Act Density 0.000%

    No Known Activations