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

    Neuronpedia

    INDEX
    Explanations

    lambda functions and list comprehensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     берегу
    0.40
     अवलंब
    0.39
     мяс
    0.39
     annen
    0.38
    TGFuZ
    0.38
    رة
    0.38
    elevationMap
    0.38
    Mâc
    0.38
    épaisseur
    0.38
    ourtney
    0.38
    POSITIVE LOGITS
     new
    0.59
     {
    0.56
    new
    0.49
    return
    0.49
    if
    0.48
     System
    0.47
     a
    0.47
     S
    0.46
     `${
    0.45
     f
    0.44
    Act Density 0.117%

    No Known Activations