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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     miglior
    -0.08
     flags
    -0.07
    ContextMenu
    -0.07
    资源优势
    -0.07
     nesta
    -0.07
    烽
    -0.07
    dcc
    -0.07
     gehen
    -0.07
    Ch
    -0.07
    Ren
    -0.07
    POSITIVE LOGITS
    {
    0.08
    asses
    0.07
    できて
    0.07
    רס
    0.07
     massac
    0.07
    ่
    0.06
     MASTER
    0.06
    (assert
    0.06
     Claud
    0.06
     traverse
    0.06
    Act Density 0.017%

    No Known Activations