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

    Neuronpedia

    INDEX
    Explanations

    references to legal citations and formal legal language

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

    Numbers followed by article "The" or numbers

    np_acts-logits-general · gemini-2.0-flash

    citation numbers and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.67
    CppMethod
    -0.62
    KommentareTeilen
    -0.60
    extAlignment
    -0.55
     contextLoads
    -0.54
    Demografía
    -0.53
    JvmStatic
    -0.52
    ruptedException
    -0.51
     INVENTION
    -0.51
    wieś
    -0.50
    POSITIVE LOGITS
     See
    0.80
    BeginContext
    0.71
    See
    0.70
    ちなみに
    0.70
     For
    0.69
    Actually
    0.67
     Actually
    0.66
     Note
    0.66
     übrigens
    0.66
     Technically
    0.65
    Act Density 0.327%

    No Known Activations