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

    Neuronpedia

    INDEX
    Explanations

    function calls and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.68
    os
    0.49
     fish
    0.44
    ics
    0.44
     cierto
    0.43
    veer
    0.42
     nich
    0.41
    cdot
    0.40
    pace
    0.40
     yıldır
    0.40
    POSITIVE LOGITS
     (){
    0.60
    к
    0.54
    (){
    0.52
    ಮ
    0.51
     Х
    0.51
    '(
    0.50
     "("
    0.50
    ()?
    0.48
    ()){
    0.47
    ?(
    0.47
    Act Density 0.041%

    No Known Activations