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

    Neuronpedia

    INDEX
    Explanations

    opportunities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쪼
    -0.08
     insurers
    -0.07
    뿍
    -0.07
    models
    -0.07
    更好
    -0.07
    ders
    -0.07
     tapered
    -0.07
    𫓯
    -0.07
    เสม
    -0.07
     typo
    -0.07
    POSITIVE LOGITS
    ![↵
    0.07
    -reset
    0.07
    ++){
↵
    0.07
    .running
    0.07
    ORIZ
    0.07
    ença
    0.07
    ingu
    0.07
    いる
    0.07
    urma
    0.06
    ----↵↵
    0.06
    Act Density 0.028%

    No Known Activations