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

    Neuronpedia

    INDEX
    Explanations

    structural and syntactical elements of programming code

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

    code structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.38
    -
    -0.33
     and
    -0.32
    /
    -0.32
    est
    -0.29
    เก
    -0.28
    もちろん
    -0.27
    e
    -0.26
     hled
    -0.25
     (
    -0.25
    POSITIVE LOGITS
    ValueStyle
    0.84
     Geiſt
    0.83
     dieſer
    0.82
    ðsíða
    0.80
     myſelf
    0.77
     dieſe
    0.77
    iſen
    0.76
     queſta
    0.76
    ſchen
    0.75
     ſehr
    0.74
    Act Density 1.935%

    No Known Activations