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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getContext
    -0.07
    .netty
    -0.07
    _play
    -0.06
    оп
    -0.06
    .gravity
    -0.06
     фрон
    -0.06
    ascal
    -0.06
    .getLeft
    -0.06
    -navbar
    -0.06
    .getRaw
    -0.06
    POSITIVE LOGITS
    (||
    0.07
     Odkazy
    0.06
    DUCT
    0.06
    June
    0.06
    216
    0.06
     Mona
    0.06
    acency
    0.06
     Crane
    0.06
    ξι
    0.06
    ."
↵
    0.06
    Act Density 0.001%

    No Known Activations