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

    Neuronpedia

    INDEX
    Explanations

    lists of companies or brands, especially those separated by conjunctions or commas

    oai_token-act-pair · gemini-2.0-flash

    company names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.68
    AndEndTag
    -0.68
    StoryboardSegue
    -0.64
     الحره
    -0.60
     nahilalakip
    -0.60
     EconPapers
    -0.59
     resourceCulture
    -0.59
    spesies
    -0.57
     transfieras
    -0.55
    XmlType
    -0.55
    POSITIVE LOGITS
     Google
    0.76
     Daimler
    0.67
    Google
    0.65
     Ford
    0.65
     Netflix
    0.64
     Activision
    0.62
     Mastercard
    0.62
     NASA
    0.61
     GOOGLE
    0.61
     FedEx
    0.59
    Act Density 1.943%

    No Known Activations