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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    This neuron detects illustrative Python code examples (especially file‐ and path‐related snippets).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    işti
    -0.08
     Steam
    -0.07
    pras
    -0.06
    ingen
    -0.06
    悪
    -0.06
     argv
    -0.06
    나라
    -0.06
     Brighton
    -0.06
     стад
    -0.06
    sqrt
    -0.05
    POSITIVE LOGITS
     distinguish
    0.07
    (guid
    0.07
     предус
    0.07
     marketers
    0.07
     BLOCK
    0.06
    ，但
    0.06
    	rc
    0.06
     GRAPH
    0.06
    写真
    0.06
    	at
    0.06
    Act Density 0.029%

    No Known Activations