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

    Neuronpedia

    INDEX
    Explanations

    occurrences of curly braces

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

    German, Japanese, Malay, punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Easter
    -0.41
     colspan
    -0.41
    AnimationsModule
    -0.41
     beyond
    -0.38
     temor
    -0.37
     other
    -0.36
     additional
    -0.36
     rechange
    -0.36
     Eastern
    -0.36
    createElement
    -0.35
    POSITIVE LOGITS
    :^{
    0.66
     daß
    0.64
     {
    0.63
    :{
    0.54
     :{
    0.54
    ={({
    0.53
    出版年
    0.53
     Bewußt
    0.53
    "{
    0.52
     bahawa
    0.51
    Act Density 0.016%

    No Known Activations