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

    Neuronpedia

    INDEX
    Explanations

    Slip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Раз
    -0.07
     dried
    -0.06
     south
    -0.06
    ח
    -0.06
    ropdown
    -0.06
     چون
    -0.06
     Vand
    -0.06
    ynam
    -0.06
    セット
    -0.06
     governors
    -0.06
    POSITIVE LOGITS
    (Output
    0.07
    'l
    0.07
     summaries
    0.07
    innerHTML
    0.06
    (withDuration
    0.06
    	Logger
    0.06
    各种
    0.06
    ;';↵
    0.06
    outfile
    0.06
    '],
↵
    0.06
    Act Density 0.001%

    No Known Activations