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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions and mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers in parentheses

    np_acts-logits-general · gemini-2.0-flash

    CALIFORNIA case citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.59
    truct
    -0.52
    ulary
    -0.51
     sopp
    -0.49
     estre
    -0.49
     "..\..\
    -0.48
     almoço
    -0.48
     Tenggara
    -0.48
     bleek
    -0.47
    Locator
    -0.47
    POSITIVE LOGITS
     محفوظة
    0.60
     demografica
    0.55
     Italijanski
    0.53
     Paglinawan
    0.51
    قایناق‌لار
    0.50
    новниш
    0.50
    makeText
    0.49
    |')
    0.49
    Спасылкі
    0.48
     referirse
    0.48
    Act Density 0.207%

    No Known Activations