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

    Neuronpedia

    INDEX
    Explanations

    braces used to denote the start of a code block in programming

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

    class and public function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    flashdata
    -0.61
     cooperación
    -0.55
     saveiro
    -0.52
    vestream
    -0.51
    MessageTagHelper
    -0.50
     rechange
    -0.50
    filepath
    -0.50
     Chwiliwch
    -0.49
    FunctionFlags
    -0.49
     ffilm
    -0.48
    POSITIVE LOGITS
     {
    1.04
     :{
    0.65
     {
    0.64
    ({
    0.64
    :{
    0.63
     ={
    0.61
    ={
    0.60
    :^{
    0.59
    ::{
    0.58
     ({
    0.57
    Act Density 0.017%

    No Known Activations