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

    Neuronpedia

    INDEX
    Explanations

    public class definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     일
    0.78
     snug
    0.77
     unim
    0.74
     SRS
    0.72
     MSU
    0.71
     -
    0.71
     Elabor
    0.71
     Scripps
    0.70
     stretch
    0.70
     upp
    0.70
    POSITIVE LOGITS
    {
    1.08
    {}{
    0.92
    tbLabel
    0.86
    (){
    0.83
    Postal
    0.83
    {\|
    0.80
    {//
    0.77
    encies
    0.76
    {[
    0.75
     tük
    0.74
    Act Density 0.020%

    No Known Activations