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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aproxim
    -0.07
     ferment
    -0.07
    strument
    -0.06
    KG
    -0.06
    幼
    -0.06
     renov
    -0.06
    ListModel
    -0.06
     mimetype
    -0.06
    (sort
    -0.06
     detalles
    -0.06
    POSITIVE LOGITS
     송
    0.08
    ariant
    0.06
    昇
    0.06
     طبی
    0.06
     잡담
    0.06
     대한민국
    0.06
     Spread
    0.05
     Israel
    0.05
    /shop
    0.05
     Zhang
    0.05
    Act Density 0.313%

    No Known Activations