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

    Neuronpedia

    INDEX
    Explanations

    Formal writing snippets

    np_max-act · gemini-2.0-flash

    This neuron responds to adverbs and other transitional or discourse-marker words (e.g., “initially,” “recently,” “officially,” “then,” “so,” “just”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -Series
    -0.06
    ilyn
    -0.06
    akening
    -0.06
     날짜
    -0.06
    Geometry
    -0.06
     princ
    -0.06
    _Space
    -0.06
    irez
    -0.06
    изнес
    -0.06
     proport
    -0.06
    POSITIVE LOGITS
    {i
    0.07
    =\"%
    0.07
     управління
    0.07
    _q
    0.06
     cruc
    0.06
     q
    0.06
     $($
    0.06
     √
    0.06
     потрібно
    0.06
     }]
    0.06
    Act Density 0.393%

    No Known Activations