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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нічого
    -0.07
     merc
    -0.07
    .null
    -0.06
    itre
    -0.06
     neste
    -0.06
     rift
    -0.06
     admired
    -0.06
     battered
    -0.06
    (sol
    -0.06
    +',
    -0.06
    POSITIVE LOGITS
    {
↵
    0.08
    ){
↵
    0.07
    (){
↵
    0.07
    ){
↵
↵
    0.07
    (){
↵
↵
    0.06
    ."""↵
    0.06
    {↵
    0.06
     삭제
    0.06
    ){↵
    0.06
    ()=>{↵
    0.06
    Act Density 0.008%

    No Known Activations