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

    Neuronpedia

    INDEX
    Explanations

    structure and continuity in narrative events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sentence endings and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     genoux
    -0.54
     wijn
    -0.48
     bambú
    -0.48
     plátano
    -0.47
     vérit
    -0.47
     veneno
    -0.47
     farine
    -0.46
    MessageTagHelper
    -0.45
    enuine
    -0.45
    eschön
    -0.44
    POSITIVE LOGITS
     oprot
    0.48
    RegressionTest
    0.47
    reactstrap
    0.42
    StoryboardSegue
    0.41
    fillType
    0.40
     defaultstate
    0.38
    wards
    0.36
     sleep
    0.35
    EndContext
    0.35
    SCAPE
    0.34
    Act Density 0.066%

    No Known Activations