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

    Neuronpedia

    INDEX
    Explanations

    the word "and" as well as the preposition "in" or geographical terms

    oai_token-act-pair · gemini-2.0-flash

    city names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     towns
    -0.58
     villagers
    -0.52
     Towns
    -0.50
     village
    -0.49
     cities
    -0.48
    akers
    -0.47
     העיר
    -0.47
    towns
    -0.46
     instanceof
    -0.46
     Nueva
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.68
    ViewImports
    0.64
    mogorov
    0.62
     EconPapers
    0.61
    XmlAccessorType
    0.58
     identifiés
    0.58
     &___
    0.57
    Становништво
    0.57
    rzost
    0.56
    醐
    0.54
    Act Density 0.199%

    No Known Activations