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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between components and systems

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

    how things connect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.47
    sufficiency
    -0.42
     sweeps
    -0.40
    úrese
    -0.40
     appré
    -0.40
    vereignty
    -0.39
    apimachinery
    -0.39
     kasarigan
    -0.39
    RegressionTest
    -0.38
     stuffing
    -0.38
    POSITIVE LOGITS
     connecting
    1.36
     connect
    1.36
     Connecting
    1.29
     connects
    1.24
    connect
    1.23
    Connecting
    1.23
     connected
    1.18
     connection
    1.16
     Connect
    1.15
    connecting
    1.13
    Act Density 0.160%

    No Known Activations