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

    Neuronpedia

    INDEX
    Explanations

    image/page counts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fight
    -0.07
     наших
    -0.07
     Hamilton
    -0.07
     diamond
    -0.07
     comes
    -0.07
     diplomats
    -0.07
     Kü
    -0.07
    	mask
    -0.06
    DEC
    -0.06
     Reading
    -0.06
    POSITIVE LOGITS
    861
    0.07
    ,id
    0.07
     {}.
    0.06
    Aw
    0.06
     Eternal
    0.06
     Craigslist
    0.06
     considerable
    0.06
    ='')↵
    0.06
    /><
    0.06
     scanning
    0.06
    Act Density 0.033%

    No Known Activations