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

    Neuronpedia

    INDEX
    Explanations

    references to the Microsoft brand and its related software components

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

    "Microsoft" followed by code-related tokens

    np_acts-logits-general · gemini-2.0-flash

    Microsoft followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uvre
    -0.54
     ref
    -0.50
    fänger
    -0.49
     tune
    -0.49
     class
    -0.49
    +'</
    -0.46
    Amos
    -0.46
     mat
    -0.45
    ığımız
    -0.45
     result
    -0.45
    POSITIVE LOGITS
    Microsoft
    1.17
     Microsoft
    1.09
     microsoft
    1.05
    microsoft
    0.83
    ContentAsync
    0.82
     виправивши
    0.81
     ***!
    0.78
    MLLoader
    0.78
    plier
    0.77
    //
    0.77
    Act Density 0.025%

    No Known Activations