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

    Neuronpedia

    INDEX
    Explanations

    specific types of nouns, particularly those related to measurements and tools

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

    two and three modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contextes
    -0.36
    组
    -0.32
    Poppins
    -0.31
     sigo
    -0.31
    elasticsearch
    -0.31
     Grüsse
    -0.31
     nya
    -0.31
     irregularity
    -0.30
     is
    -0.29
    кість
    -0.29
    POSITIVE LOGITS
     resourceCulture
    0.62
    complexContent
    0.60
    makeText
    0.57
    tvguidetime
    0.56
    StoryboardSegue
    0.56
     ویکی‌پدی
    0.54
    GEBURTS
    0.54
     مرئيه
    0.52
    wreck
    0.51
    ScopeManager
    0.50
    Act Density 0.075%

    No Known Activations