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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash

    The neuron detects fragments of file system paths (e.g. backslashes and directory or filename tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (Path
    -0.06
     Toledo
    -0.06
     очи
    -0.06
     Julie
    -0.06
     Milano
    -0.06
    Unary
    -0.06
     Fly
    -0.06
    _NULL
    -0.06
    Ｙ
    -0.06
     gad
    -0.06
    POSITIVE LOGITS
    صح
    0.07
    -offsetof
    0.06
    _signature
    0.06
     www
    0.06
     anyways
    0.06
    	constructor
    0.06
    @protocol
    0.06
    ?>">↵
    0.06
     списка
    0.06
    (animation
    0.06
    Act Density 0.053%

    No Known Activations