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

    Neuronpedia

    INDEX
    Explanations

    geopolitical news

    np_max-act · gemini-2.0-flash

    This neuron responds to abstract political‐analysis language—especially nominalized concepts (assessment, challenges, contradiction), modal/forecasting expressions (chances, seems, certainly), and other high-level discourse terms that discuss evaluations or future possibilities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ADF
    -0.07
    аного
    -0.06
    방법
    -0.06
     lodash
    -0.06
    ALES
    -0.06
    Procedure
    -0.06
    idas
    -0.06
    ثل
    -0.06
    ِب
    -0.06
     rozs
    -0.06
    POSITIVE LOGITS
     questi
    0.07
    /div
    0.06
     справа
    0.06
    Immediate
    0.06
    Predict
    0.06
    .metroLabel
    0.06
    /forum
    0.06
     #-
    0.06
     deadlock
    0.06
    	send
    0.06
    Act Density 0.022%

    No Known Activations