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

    Neuronpedia

    INDEX
    Explanations

    titles and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.45
    <unused2018>
    0.42
    (−
    0.39
    ᇂ
    0.39
    <unused281>
    0.39
    <unused722>
    0.38
     omdat
    0.38
    ᆸ
    0.38
    <unused491>
    0.38
    েন্ত্র
    0.37
    POSITIVE LOGITS
    .,
    0.66
    .;
    0.47
    ed
    0.43
    ש
    0.43
    .
    0.41
    .:
    0.41
    etera
    0.39
    ./
    0.39
    S
    0.39
    .-
    0.39
    Act Density 0.100%

    No Known Activations