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

    Neuronpedia

    INDEX
    Explanations

    legal writing

    np_max-act · gemini-2.0-flash

    This neuron activates on boilerplate patent‐style phrases that introduce or refer to the detailed description (e.g. “description is provided in this regard”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     місце
    -0.06
    anye
    -0.06
     Hort
    -0.06
     Chip
    -0.06
     waste
    -0.06
     asleep
    -0.06
    される
    -0.06
    ila
    -0.06
     hides
    -0.06
     Grid
    -0.06
    POSITIVE LOGITS
     организа
    0.07
    Installation
    0.07
     Infragistics
    0.07
    	arg
    0.07
     etmeye
    0.07
    -created
    0.06
    [Boolean
    0.06
    Writable
    0.06
    clang
    0.06
     společnost
    0.06
    Act Density 0.042%

    No Known Activations