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

    Neuronpedia

    INDEX
    Explanations

    numeric or coded values in structured data

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

    Code-related keywords or identifiers

    np_acts-logits-general · gemini-2.0-flash

    protobuf field serialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HEND
    -0.47
     Yama
    -0.47
     sheet
    -0.46
     Arxiv
    -0.46
    gifs
    -0.46
     Houſe
    -0.45
     screen
    -0.45
     NSMutable
    -0.45
    findBy
    -0.45
    又
    -0.44
    POSITIVE LOGITS
     createStore
    0.71
    RectangleBorder
    0.61
     ivelany
    0.59
          
    0.59
     wireType
    0.56
     AssemblyCompany
    0.55
    нодоро
    0.54
    0.53
     protoimpl
    0.53
    lorette
    0.53
    Act Density 0.103%

    No Known Activations