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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to questions, requests, or communication

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

    to tell me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.63
    addCriterion
    -0.57
    setVerticalGroup
    -0.55
    StructEnd
    -0.54
    SuccessListener
    -0.53
    🔕
    -0.53
    TextWatcher
    -0.52
    yntaxException
    -0.52
    MigrationBuilder
    -0.51
    MethodManager
    -0.50
    POSITIVE LOGITS
    告诉我
    0.38
    Edge
    0.35
     me
    0.35
     bize
    0.35
    叫我
    0.35
    me
    0.33
    Leg
    0.33
    ว
    0.33
    让我
    0.32
    向
    0.32
    Act Density 0.207%

    No Known Activations