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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code snippets related to programming, particularly within the context of HTTP and document structure

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

    tech, legal, and archaic texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     co
    -0.55
     
    -0.49
     on
    -0.46
     la
    -0.46
     for
    -0.45
     bu
    -0.44
     U
    -0.44
     to
    -0.44
    <strong>
    -0.43
     I
    -0.43
    POSITIVE LOGITS
     itſelf
    1.02
     Majefty
    1.00
     Reſ
    1.00
     ―――――
    0.98
    ſelves
    0.98
     themſelves
    0.98
    mobileqq
    0.97
     Jefus
    0.96
     leaſt
    0.96
     ſeveral
    0.95
    Act Density 0.147%

    No Known Activations