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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iets
    -0.07
    .business
    -0.07
     수강
    -0.07
    .inner
    -0.07
     UNIVERS
    -0.07
    utr
    -0.06
    	User
    -0.06
     Subset
    -0.06
    ایج
    -0.06
    chyb
    -0.06
    POSITIVE LOGITS
     />
    0.07
    ---↵↵
    0.06
    -,
    0.06
    >\
    0.06
    '>
    0.06
     ").
    0.06
     (>
    0.06
    lin
    0.06
     ';↵↵
    0.06
    Export
    0.06
    Act Density 0.002%

    No Known Activations