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

    Neuronpedia

    INDEX
    Explanations

    src

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of source‐directory path tokens (e.g. “src” in file paths).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ge
    -0.07
    ley
    -0.07
     Economic
    -0.07
    finite
    -0.07
     Peace
    -0.07
     mappings
    -0.07
     collective
    -0.06
    =my
    -0.06
     heed
    -0.06
     covenant
    -0.06
    POSITIVE LOGITS
    /src
    0.09
     src
    0.08
    SCR
    0.08
    ск
    0.07
     SRC
    0.07
    (InitializedTypeInfo
    0.07
     مرکزی
    0.07
    RPC
    0.07
     Exc
    0.07
    rc
    0.07
    Act Density 0.005%

    No Known Activations