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

    Neuronpedia

    INDEX
    Explanations

    URL patterns and API endpoint structures in code

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

    URL paths and routes

    np_acts-logits-general · gemini-2.0-flash

    URLs with slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.73
     المعيارى
    -0.66
    enterOuterAlt
    -0.61
    AddTagHelper
    -0.59
    StoreMessageInfo
    -0.56
    OGND
    -0.55
    SharedCtor
    -0.55
     queſta
    -0.54
    mergeFrom
    -0.54
    ScopeManager
    -0.53
    POSITIVE LOGITS
     urm
    0.44
    urtstag
    0.42
    ⡀
    0.40
    nasium
    0.39
     following
    0.39
    xnn
    0.38
    HStack
    0.38
    Un
    0.38
    更
    0.37
     सर
    0.37
    Act Density 0.067%

    No Known Activations