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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash

    This neuron strongly activates on occurrences of the word “used” (especially in passive‐voice method descriptions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    .pagination
    -0.06
     riv
    -0.06
     abundance
    -0.06
    division
    -0.06
    /loading
    -0.06
    setParameter
    -0.06
    isure
    -0.06
    .Logging
    -0.06
    Ö
    -0.06
    POSITIVE LOGITS
     used
    0.07
     Cisco
    0.06
     Used
    0.06
     Designed
    0.06
     formulaire
    0.06
    [file
    0.06
     ↵↵↵↵↵
    0.06
     each
    0.06
    	static
    0.06
     ↵  ↵
    0.06
    Act Density 0.011%

    No Known Activations