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

    Neuronpedia

    INDEX
    Explanations

    x, y, z, p, n, formula

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    securityMarks
    0.41
    اونلو
    0.37
    >∕
    0.36
     équipe
    0.36
    getImageFolder
    0.35
    监狱
    0.35
    <unused71>
    0.35
    öffentlich
    0.35
    Methylsulfanyl
    0.35
    સભા
    0.34
    POSITIVE LOGITS
     =
    0.45
    .
    0.45
    i
    0.45
    N
    0.45
    I
    0.43
     in
    0.43
    =
    0.42
    max
    0.42
    as
    0.42
    that
    0.41
    Act Density 0.172%

    No Known Activations