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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash

    This neuron detects JavaScript code snippets, firing on code‐specific tokens like variable names, punctuation, and function syntax.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Choose
    -0.08
     Install
    -0.07
     LLC
    -0.07
    clinic
    -0.07
    small
    -0.06
    _repo
    -0.06
     보면
    -0.06
    Forever
    -0.06
     arises
    -0.06
    Enumer
    -0.06
    POSITIVE LOGITS
     GameManager
    0.07
     hydr
    0.07
    (ray
    0.07
    wed
    0.06
    antage
    0.06
    /;↵
    0.06
    alertView
    0.06
    >Action
    0.06
     крок
    0.06
    �
    0.06
    Act Density 0.020%

    No Known Activations