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

    Neuronpedia

    INDEX
    Explanations

    braces that indicate the beginning and ending of code blocks in programming languages

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

    a generic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſch
    -0.70
    tagHelperRunner
    -0.69
     faſt
    -0.67
    FunctionFlags
    -0.66
     ſou
    -0.65
     vPvB
    -0.64
     saveiro
    -0.61
     Chwiliwch
    -0.60
     pérd
    -0.60
     мәкал
    -0.60
    POSITIVE LOGITS
    {
    0.75
    :{
    0.57
    {
    0.55
     {
    0.52
    :
    0.52
    ({
    0.51
    :{
    0.48
    '{
    0.47
    ::{
    0.47
    a
    0.46
    Act Density 0.004%

    No Known Activations