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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -even
    -0.07
     chip
    -0.07
     curated
    -0.06
     estimator
    -0.06
     ül
    -0.06
     create
    -0.06
    іх
    -0.06
    ign
    -0.06
     weave
    -0.06
     yol
    -0.06
    POSITIVE LOGITS
     gelecek
    0.07
     širo
    0.07
    !");↵↵
    0.07
     '/../
    0.06
     stalled
    0.06
     específ
    0.06
    ++);↵
    0.06
    	desc
    0.06
    <=
    0.06
     espaço
    0.06
    Act Density 0.019%

    No Known Activations