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

    Neuronpedia

    INDEX
    Explanations

    sequences of underscores or placeholders indicating omitted information

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

    initiation, olu, hoku, quad, Next

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rawDesc
    -0.62
     queſta
    -0.55
    fxml
    -0.53
     laſſen
    -0.53
     zoude
    -0.53
    databind
    -0.52
    bootstrapcdn
    -0.52
    เดียว
    -0.52
     $_"
    -0.51
    hicles
    -0.50
    POSITIVE LOGITS
    AsUp
    0.42
     noDo
    0.39
     Northumberland
    0.36
    -------
    0.35
     ब्रेकडाउन
    0.35
     Xue
    0.34
    лактика
    0.34
     OFDb
    0.33
     BrowserModule
    0.32
    0.31
    Act Density 0.249%

    No Known Activations