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

    Neuronpedia

    INDEX
    Explanations

    Code delimiters

    np_max-act · gemini-2.0-flash

    examples of code implementation and usage of Python's print function.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects backtick characters (``` or `) used to mark code spans or code fences.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Neal
    -0.07
     runners
    -0.06
    æk
    -0.06
     meals
    -0.06
     -*-
↵
    -0.06
    ！！
    -0.06
    Tel
    -0.06
    ück
    -0.06
     applicants
    -0.06
     Idea
    -0.06
    POSITIVE LOGITS
     cpt
    0.07
    [array
    0.07
     userID
    0.06
     disin
    0.06
    ğimiz
    0.06
    -shot
    0.06
    овые
    0.06
     Syrians
    0.06
    crew
    0.06
     admir
    0.06
    Act Density 0.014%

    No Known Activations