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

    Neuronpedia

    INDEX
    Explanations

    path

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the identifier “path” (e.g. module imports or variable names referring to file‐system paths).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Grinder
    -0.09
     eleştir
    -0.07
     vere
    -0.07
    oren
    -0.07
    izzer
    -0.07
    _enter
    -0.07
     Simone
    -0.06
     uveden
    -0.06
    .general
    -0.06
     Drill
    -0.06
    POSITIVE LOGITS
     Path
    0.16
    Path
    0.15
     path
    0.14
    path
    0.13
    .Path
    0.11
    _path
    0.11
     paths
    0.11
    	Path
    0.10
    -path
    0.10
     Paths
    0.10
    Act Density 0.047%

    No Known Activations