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

    Neuronpedia

    INDEX
    Explanations

    code and markdown formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     тобто
    0.39
     તમામ
    0.38
     namelijk
    0.36
    ⠀⠀⠀⠀
    0.35
    *:
    0.35
    ​.
    0.35
     രണ്ട്
    0.35
    isodes
    0.34
    ¹.
    0.34
    नेश
    0.33
    POSITIVE LOGITS
     %``
    0.63
     {@
    0.52
     ‫
    0.52
     ‪
    0.47
    0.46
    《
    0.45
    ॒
    0.44
    <strong>
    0.42
     `
    0.41
     《
    0.40
    Act Density 0.156%

    No Known Activations