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

    Neuronpedia

    INDEX
    Explanations

    specific programming or mathematical symbols and syntax

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

    fraction or power notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.63
    UseVisualStyle
    -0.63
    TagMode
    -0.63
    httphttps
    -0.62
     Normdatei
    -0.61
    findpost
    -0.60
    ⓧ
    -0.59
    UserScript
    -0.57
     Numerade
    -0.54
    AddTagHelper
    -0.54
    POSITIVE LOGITS
     elsewhere
    0.41
    <eos>
    0.37
     كم
    0.33
    寞
    0.33
    ?).
    0.33
    elang
    0.33
     generic
    0.33
    ?)
    0.33
     suc
    0.32
    furt
    0.32
    Act Density 0.111%

    No Known Activations