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

    Neuronpedia

    INDEX
    Explanations

    close to or larger than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тра
    0.42
    今回の
    0.42
     ontwikkel
    0.42
     vertrou
    0.39
    пла
    0.39
    思维
    0.38
    <unused21>
    0.37
     ihres
    0.37
    нутри
    0.37
     ihren
    0.37
    POSITIVE LOGITS
    number
    0.46
    NUMBER
    0.46
    lllll
    0.45
     pirm
    0.44
     centru
    0.43
    llll
    0.42
    because
    0.42
     number
    0.42
     pirates
    0.41
    eqn
    0.41
    Act Density 0.001%

    No Known Activations