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

    Neuronpedia

    INDEX
    Explanations

    nested structures in code or data

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

    Code delimiters or brackets

    np_acts-logits-general · gemini-2.0-flash

    `<start_of_turn>` user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſch
    -0.64
    GenerationType
    -0.59
     lenker
    -0.58
     faſt
    -0.57
    mybatisplus
    -0.56
    rungsseite
    -0.55
     Keaton
    -0.54
     GoogleFonts
    -0.53
     AssemblyVersion
    -0.53
     gonzález
    -0.53
    POSITIVE LOGITS
    {
    0.79
    :{
    0.65
     {
    0.60
    ({
    0.58
    '{
    0.57
    ::{
    0.56
     "{
    0.53
    "{
    0.53
    \{
    0.52
    ("{
    0.52
    Act Density 0.083%

    No Known Activations