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

    Neuronpedia

    INDEX
    Explanations

    code-related constructs such as function definitions and variable declarations

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

    Technical or networking-related terms

    np_acts-logits-general · gemini-2.0-flash

    TCP sockets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    flug
    -0.39
     ValidationError
    -0.39
     itemprop
    -0.38
    棚
    -0.38
    хов
    -0.37
    kmale
    -0.36
    inture
    -0.36
    lardır
    -0.36
     confira
    -0.35
    SuppressWarnings
    -0.35
    POSITIVE LOGITS
     socket
    1.18
     Socket
    1.16
    socket
    1.08
     client
    1.07
    Socket
    1.06
     Client
    1.02
     sockets
    1.00
     communication
    1.00
     server
    0.99
     ProtoMessage
    0.97
    Act Density 0.640%

    No Known Activations