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

    Neuronpedia

    INDEX
    Explanations

    geometrical spatial relations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     style
    -0.07
     Ub
    -0.07
     recreational
    -0.07
     upgrade
    -0.07
     centuries
    -0.07
     id
    -0.07
     ID
    -0.07
     Freizeit
    -0.07
    SE
    -0.07
     ||
    -0.07
    POSITIVE LOGITS
     দিকে
    0.10
    раҡ
    0.09
     سمت
    0.09
     conecta
    0.08
    -ish
    0.08
    .diagram
    0.08
     şeyi
    0.08
    ерг
    0.08
     بـ
    0.08
     naho
    0.08
    Act Density 0.023%

    No Known Activations