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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming functions and events

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

    after specific method or function names

    np_acts-logits-general · gemini-2.0-flash

    programming terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    -0.97
     
    -0.96
     a
    -0.96
     y
    -0.95
     "
    -0.94
     vi
    -0.92
     so
    -0.92
     to
    -0.90
     n
    -0.88
     v
    -0.87
    POSITIVE LOGITS
     Anſ
    2.08
     Reſ
    2.00
     Houſe
    1.99
     Monfieur
    1.97
     Efq
    1.96
     Jefus
    1.94
     itſelf
    1.90
     Majefty
    1.87
     Diſ
    1.87
    ſelf
    1.86
    Act Density 1.060%

    No Known Activations