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

    Neuronpedia

    INDEX
    Explanations

    latex referencing and graphics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Episodes
    0.40
    familiar
    0.37
     Guinness
    0.36
    તાવ
    0.35
    Episodes
    0.34
     ALLO
    0.33
     CYCLE
    0.33
     Food
    0.33
    alb
    0.33
     नाते
    0.33
    POSITIVE LOGITS
    {
    0.76
     {
    0.70
    []{
    0.57
    *{
    0.56
    {\
    0.53
    {\'
    0.53
    {-
    0.52
    {}{
    0.51
    ]{
    0.48
    {``
    0.48
    Act Density 0.004%

    No Known Activations