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

    Neuronpedia

    INDEX
    Explanations

    proc

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of the Linux “proc” pseudo‐filesystem (i.e. occurrences of “proc” in paths like “/proc/…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    558
    -0.07
    227
    -0.06
     Earlier
    -0.06
     champions
    -0.06
     dalle
    -0.06
    former
    -0.06
    یط
    -0.06
    IED
    -0.06
    223
    -0.06
    phyl
    -0.06
    POSITIVE LOGITS
    Proc
    0.09
     PROC
    0.09
     proc
    0.08
     procure
    0.08
     procur
    0.08
    _proc
    0.07
    _probe
    0.07
    _proto
    0.07
    uci
    0.07
     Customs
    0.07
    Act Density 0.007%

    No Known Activations