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

    Neuronpedia

    INDEX
    Explanations

    Code snippets/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ераль
    -0.07
     có
    -0.06
     고개를
    -0.06
     extents
    -0.06
     ч
    -0.06
    ance
    -0.06
     bureaucr
    -0.06
    ned
    -0.06
    ану
    -0.06
     фін
    -0.06
    POSITIVE LOGITS
     {
    0.08
    珠
    0.07
    /wp
    0.06
     ddl
    0.06
    _che
    0.06
    .lat
    0.06
    
    0.06
    Conv
    0.06
    (AT
    0.06
    ******
↵
    0.06
    Act Density 0.000%

    No Known Activations