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

    Neuronpedia

    INDEX
    Explanations

    Court

    np_max-act · gemini-2.0-flash

    The neuron detects court‐of‐appeals headings, specifically spotting mentions of “Court of Appeals” (e.g. “Michigan Court of Appeals”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    มาก
    -0.06
    ías
    -0.06
     Champions
    -0.06
     tang
    -0.06
    arkin
    -0.06
    опри
    -0.06
    144
    -0.06
     fees
    -0.06
     caffeine
    -0.06
    Rank
    -0.06
    POSITIVE LOGITS
    (Name
    0.07
     вул
    0.06
     soudu
    0.06
     charismatic
    0.06
    "The
    0.06
    	inst
    0.06
    _TYPEDEF
    0.06
                
↵
    0.06
     forIndexPath
    0.06
    _"
    0.06
    Act Density 0.001%

    No Known Activations