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

    Neuronpedia

    INDEX
    Explanations

    diversity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     поверхности
    -0.06
    ytt
    -0.06
    üsü
    -0.06
    음을
    -0.06
     peninsula
    -0.06
    iants
    -0.06
    gtest
    -0.06
    富
    -0.06
     Dota
    -0.06
    KA
    -0.06
    POSITIVE LOGITS
    _fw
    0.06
    ppt
    0.06
     :)↵
    0.06
     приводит
    0.06
    	dist
    0.06
     indirect
    0.06
    Listening
    0.06
     xy
    0.06
    (EVENT
    0.06
    _Block
    0.06
    Act Density 0.000%

    No Known Activations