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

    Neuronpedia

    INDEX
    Explanations

    minute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     test
    -0.06
    	Initialize
    -0.06
    Verbose
    -0.06
     상세
    -0.06
    发布
    -0.06
    ivative
    -0.06
     opera
    -0.06
    urrencies
    -0.06
    berra
    -0.06
     pedigree
    -0.06
    POSITIVE LOGITS
     Mong
    0.07
    лади
    0.07
     substitutions
    0.07
    spr
    0.07
     brink
    0.07
    ')}</
    0.06
    藥
    0.06
     quem
    0.06
     opted
    0.06
    fg
    0.06
    Act Density 0.003%

    No Known Activations