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

    Neuronpedia

    INDEX
    Explanations

    specific programming or technical terminology related to data handling and control systems

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

    Capitalized words after certain punctuation

    np_acts-logits-general · gemini-2.0-flash

    archaic reflexive pronouns and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -0.70
     
    -0.62
     a
    -0.60
     so
    -0.60
    </i>
    -0.59
     “
    -0.59
     qu
    -0.57
     s
    -0.56
     in
    -0.56
     an
    -0.56
    POSITIVE LOGITS
     myſelf
    1.54
     itſelf
    1.51
     Monfieur
    1.46
     Majefty
    1.37
     Jefus
    1.35
     Efq
    1.34
     Reſ
    1.31
     Anſ
    1.30
     pleaſure
    1.27
     himſelf
    1.26
    Act Density 0.722%

    No Known Activations