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

    Neuronpedia

    INDEX
    Explanations

    the word "on" followed by punctuation or another word

    oai_token-act-pair · gemini-2.0-flash

    set/sets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.50
    IUrlHelper
    -0.49
    Режи
    -0.49
    LabelTagHelper
    -0.47
    fertigt
    -0.46
    })$}
    -0.45
    addProduct
    -0.45
    :][
    -0.45
    runApp
    -0.44
    Ủ
    -0.44
    POSITIVE LOGITS
     set
    2.48
     sets
    2.20
     Set
    2.00
    set
    1.89
     Sets
    1.88
    Set
    1.82
     SET
    1.70
    Sets
    1.63
    sets
    1.60
     SETS
    1.57
    Act Density 2.140%

    No Known Activations