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 parent‐directory path segments (i.e. “../” sequences) in file paths.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     jit
    -0.07
     retailers
    -0.06
     datatype
    -0.06
    배송
    -0.06
    Hold
    -0.06
     setDefaultCloseOperation
    -0.06
     někter
    -0.06
     ruthless
    -0.06
     Nem
    -0.06
    tokenId
    -0.06
    POSITIVE LOGITS
    ../
    0.08
    ../../
    0.08
     Duncan
    0.08
    ='../
    0.07
    ../
    0.07
    ("../
    0.07
     cheese
    0.07
     Consequently
    0.07
     consequently
    0.07
    ../../../../
    0.07
    Act Density 0.006%

    No Known Activations