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

    Neuronpedia

    INDEX
    Explanations

    biology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LEAR
    -0.06
     conceive
    -0.06
    远
    -0.06
     checked
    -0.06
     feed
    -0.06
     feeds
    -0.06
    ilib
    -0.06
     /*↵
    -0.06
     résultats
    -0.06
    greater
    -0.06
    POSITIVE LOGITS
    rid
    0.07
    429
    0.06
    нима
    0.06
     отдел
    0.06
     Intelligence
    0.06
     علي
    0.06
    /uploads
    0.06
    íl
    0.06
     crimes
    0.06
     boyunca
    0.06
    Act Density 0.013%

    No Known Activations