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

    Neuronpedia

    INDEX
    Explanations

    Austin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �蛛
    -0.08
    YPE
    -0.07
    .notifyDataSetChanged
    -0.07
     WORD
    -0.07
     WR
    -0.07
    .protobuf
    -0.07
    _mas
    -0.07
     κα
    -0.06
     phố
    -0.06
    	load
    -0.06
    POSITIVE LOGITS
     Austin
    0.22
    Austin
    0.19
     Justin
    0.11
    Justin
    0.10
     Aust
    0.09
    ustin
    0.08
    ст
    0.08
    stein
    0.08
    sten
    0.07
    青
    0.07
    Act Density 0.003%

    No Known Activations