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

    Neuronpedia

    INDEX
    Explanations

    references to natural language processing concepts and methodologies.

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

    various types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.27
     being
    0.23
     inti
    0.22
     aneurysm
    0.22
     להיות
    0.22
     that
    0.21
     ছয়
    0.21
     triage
    0.21
     cannula
    0.21
     ";"
    0.21
    POSITIVE LOGITS
     soorten
    0.35
    types
    0.31
     types
    0.30
     countries
    0.30
    異なる
    0.28
    تي
    0.28
    の種類
    0.28
     других
    0.27
    種類
    0.27
     ఇతర
    0.27
    Act Density 0.356%

    No Known Activations