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

    Neuronpedia

    INDEX
    Explanations

    indents and structured formatting in programming code

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

    Code context: "else", "var", "for", "return"

    np_acts-logits-general · gemini-2.0-flash

    programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    -0.68
     ass
    -0.67
     of
    -0.65
     amp
    -0.63
     to
    -0.63
     li
    -0.62
     L
    -0.61
     t
    -0.60
     on
    -0.60
     met
    -0.60
    POSITIVE LOGITS
     myſelf
    1.14
     itſelf
    1.06
     pleaſure
    1.05
     ſmall
    1.04
     themſelves
    1.02
     purpoſe
    1.00
     greateſt
    0.99
    //
    0.99
     дописавши
    0.97
     reaſon
    0.96
    Act Density 0.823%

    No Known Activations