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

    Neuronpedia

    INDEX
    Explanations

    list items or points in a structured format

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

    bullet points or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.68
    enumi
    -0.63
    exitRule
    -0.54
    ViewFeatures
    -0.51
    curities
    -0.50
    ItemBackground
    -0.49
    neurial
    -0.48
    __":
    -0.47
     Italijani
    -0.46
     Consolidated
    -0.46
    POSITIVE LOGITS
     externi
    0.54
    InjectAttribute
    0.52
    GEBURTSDATUM
    0.49
    FXML
    0.47
     relâche
    0.46
     cherchés
    0.44
     defaultstate
    0.43
    0.42
    tagPool
    0.41
    sidemargin
    0.41
    Act Density 0.032%

    No Known Activations