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

    Neuronpedia

    INDEX
    Explanations

    variable assignment and declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isang
    0.55
    -,
    0.51
     een
    0.47
     copious
    0.47
     нее
    0.46
     yksi
    0.46
     one
    0.45
    ."),
    0.45
     opportune
    0.44
     numerous
    0.43
    POSITIVE LOGITS
     =
    0.72
    (){
    0.59
    ():
    0.58
    Wrapper
    0.56
     :=
    0.55
    ();
    0.55
    ()
    0.55
     ={
    0.54
    ={
    0.54
    Cache
    0.54
    Act Density 0.537%

    No Known Activations