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

    Neuronpedia

    INDEX
    Explanations

    references to time periods and money

    oai_token-act-pair · gemini-2.0-flash

    measures of financial change

    np_token-act-pair-logits · gpt-4o-mini

    comparison

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expandindo
    -1.23
    didSet
    -1.10
     للمعارف
    -1.04
    tvguidetime
    -1.02
     resourceCulture
    -1.02
     kaarangay
    -1.00
    WebServlet
    -0.98
    GEBURTSDATUM
    -0.96
    ScopeManager
    -0.93
    énario
    -0.93
    POSITIVE LOGITS
     more
    0.57
     less
    0.56
    let
    0.52
    ine
    0.51
    less
    0.48
     brevi
    0.46
     let
    0.46
    end
    0.46
    San
    0.45
     longer
    0.45
    Act Density 3.026%

    No Known Activations