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

    Neuronpedia

    INDEX
    Explanations

    occurrences of escape characters or symbols used in programming or mathematical notation

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

    mathematical formulas and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.91
    Tikang
    -0.88
     otomatig
    -0.84
    principalColumn
    -0.83
     propOrder
    -0.78
     Мексичка
    -0.75
    Datuak
    -0.75
    XmlAccessType
    -0.74
    AddTagHelper
    -0.73
    SequentialGroup
    -0.72
    POSITIVE LOGITS
    \
    0.48
     the
    0.46
    s
    0.45
    ↵
    0.39
     film
    0.35
     workshop
    0.30
    :
    0.30
     she
    0.29
    ::
    0.29
     raya
    0.29
    Act Density 0.002%

    No Known Activations