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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пож
    -0.07
     unborn
    -0.06
     раск
    -0.06
     Rank
    -0.06
     Driving
    -0.06
     Раз
    -0.06
     Sessions
    -0.06
     Bermuda
    -0.06
     İs
    -0.06
     '"';↵
    -0.06
    POSITIVE LOGITS
    undra
    0.06
    xyz
    0.06
    ↑
    0.06
    нения
    0.06
    employment
    0.06
    PATCH
    0.06
     honoring
    0.06
    stricted
    0.06
     Category
    0.06
     advisor
    0.06
    Act Density 0.000%

    No Known Activations