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

    Neuronpedia

    INDEX
    Explanations

    content related to technical terms and functionality in programming or biology

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

    HTML attributes and tags

    np_acts-logits-general · gemini-2.0-flash

    HTML tags and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.89
     fubject
    -0.85
     myſelf
    -0.84
     pleaſure
    -0.83
     Reſ
    -0.79
     itſelf
    -0.79
     becauſe
    -0.78
     Theſe
    -0.77
     poffible
    -0.77
     Monfieur
    -0.77
    POSITIVE LOGITS
     [
    0.59
    GroupLayout
    0.57
     (
    0.50
     fear
    0.47
     x
    0.47
     mo
    0.46
    class
    0.46
     real
    0.46
     Real
    0.44
    at
    0.44
    Act Density 0.191%

    No Known Activations