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

    Neuronpedia

    INDEX
    Explanations

    unique structures or characteristics of systems, particularly in a scientific context

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

    something is uncommon or exceptional

    np_acts-logits-general · gemini-2.0-flash

    unparalleled, rare, unique situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    middels
    -0.72
    initComponents
    -0.57
     AssemblyVersion
    -0.55
    AccessorTable
    -0.54
    IsContent
    -0.53
     tématu
    -0.52
    astéroïdes
    -0.52
     StringTokenizer
    -0.52
    queryInterface
    -0.51
    gonic
    -0.51
    POSITIVE LOGITS
     rare
    1.43
     rarity
    1.33
     unique
    1.15
    rare
    1.13
     unprecedented
    1.11
    Rare
    1.11
     rarest
    1.10
     Rare
    1.06
     unusual
    1.05
     rarely
    1.02
    Act Density 0.230%

    No Known Activations