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

    Neuronpedia

    INDEX
    Explanations

    interaction

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “interaction” (and its variants) in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     calcul
    -0.08
     schedule
    -0.08
     launch
    -0.07
     pid
    -0.07
     scheduled
    -0.07
     calculates
    -0.07
     latitude
    -0.07
     planning
    -0.07
     planned
    -0.07
    (column
    -0.07
    POSITIVE LOGITS
     interact
    0.12
     Interaction
    0.09
     interacts
    0.09
     interaction
    0.08
     interacting
    0.08
    _mob
    0.08
    interaction
    0.08
    орот
    0.07
    交流
    0.07
    тим
    0.07
    Act Density 0.023%

    No Known Activations