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

    Neuronpedia

    INDEX
    Explanations

    scientific study methods

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on words and phrases that introduce or describe a study’s methodology (e.g. “data from,” “cohort,” “study setting,” “methods,” “longitudinal”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    писание
    -0.07
    -refresh
    -0.07
     LX
    -0.06
     podcasts
    -0.06
    ersions
    -0.06
     une
    -0.06
     folding
    -0.06
     STL
    -0.06
     hwnd
    -0.06
    _IMPORTED
    -0.06
    POSITIVE LOGITS
    (record
    0.06
     �
    0.06
    letics
    0.06
    ��
    0.06
    igen
    0.06
     √
    0.06
    (newState
    0.06
     programme
    0.06
    omik
    0.06
     Gins
    0.06
    Act Density 0.034%

    No Known Activations