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

    Neuronpedia

    INDEX
    Explanations

    references to Microsoft and its related products or concepts

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

    "Microsoft" or "micro"

    np_acts-logits-general · gemini-2.0-flash

    Microsoft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    -0.45
    ayy
    -0.42
    stay
    -0.41
    loys
    -0.40
    warn
    -0.40
    autonomie
    -0.39
     बन
    -0.39
     νό
    -0.38
     aanv
    -0.38
    say
    -0.38
    POSITIVE LOGITS
    Microsoft
    0.81
    microsoft
    0.80
    MICRO
    0.77
     Micros
    0.76
     MICRO
    0.75
    Micro
    0.75
     microsoft
    0.75
    Micros
    0.74
     Microsoft
    0.73
     Micro
    0.73
    Act Density 0.181%

    No Known Activations