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

    Neuronpedia

    INDEX
    Explanations

    brands, companies, or products in a business context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    recognizes compound brand names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    googleapis
    -0.51
      
    -0.49
     must
    -0.47
     com
    -0.47
     present
    -0.47
     in
    -0.46
    imdb
    -0.46
     let
    -0.45
    DEVICES
    -0.45
    ynb
    -0.44
    POSITIVE LOGITS
     Jefus
    0.84
     Majefty
    0.83
     houſe
    0.81
     Paglinawan
    0.81
    دانشنامهٔ
    0.80
     Houſe
    0.79
    addCriterion
    0.79
     himo
    0.78
    LookAnd
    0.78
     itſelf
    0.77
    Act Density 0.509%

    No Known Activations