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

    Neuronpedia

    INDEX
    Explanations

    networkx library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    errals
    -0.07
    讶
    -0.07
    欲
    -0.07
    Coordinates
    -0.06
    력을
    -0.06
    賦
    -0.06
    Syntax
    -0.06
    几百
    -0.06
    拼搏
    -0.06
    ,List
    -0.06
    POSITIVE LOGITS
     بي
    0.08
    集成
    0.07
     Slots
    0.07
     DIR
    0.07
    (lib
    0.07
    itates
    0.07
    -all
    0.07
    ::{
    0.07
     פתוח
    0.07
    Es
    0.06
    Act Density 0.006%

    No Known Activations