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

    Neuronpedia

    INDEX
    Explanations

    /socket

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of socket‐related system header includes (e.g. any “sys/socket.h”–style include).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Calories
    -0.06
     Conversely
    -0.06
     Cable
    -0.06
    "strconv
    -0.06
     artillery
    -0.06
     malloc
    -0.06
     Ernst
    -0.06
     чим
    -0.06
    arrera
    -0.06
    969
    -0.06
    POSITIVE LOGITS
     typeof
    0.07
     create
    0.06
    .multi
    0.06
    лика
    0.06
     dram
    0.06
    silent
    0.06
    sock
    0.06
    -rounded
    0.06
     "<?
    0.06
    ejte
    0.06
    Act Density 0.004%

    No Known Activations