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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting programming identifiers—names of functions, types, variables, or constants (often in CamelCase or snake/upper‐case) in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     suede
    -0.07
    ็ค
    -0.06
     Hou
    -0.06
     тобі
    -0.06
    .two
    -0.06
     dij
    -0.06
    ちょっと
    -0.06
     Notre
    -0.06
    book
    -0.06
    uma
    -0.06
    POSITIVE LOGITS
     warehouses
    0.07
    GroupId
    0.07
    _WIDGET
    0.06
    .LayoutInflater
    0.06
    ，其
    0.06
    Shift
    0.06
    _wheel
    0.06
    _sources
    0.06
    _library
    0.06
     सम
    0.06
    Act Density 0.072%

    No Known Activations