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

    Neuronpedia

    INDEX
    Explanations

    structural elements and formatting tokens in code or text

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

    tft string set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.65
    rungsseite
    -0.62
    الإنجليزية
    -0.58
    sizeCache
    -0.56
    حياته
    -0.55
     betweenstory
    -0.53
    writeFieldEnd
    -0.53
     okuyayım
    -0.52
    SceneManagement
    -0.51
    bcryptjs
    -0.51
    POSITIVE LOGITS
    T
    0.71
     T
    0.69
     t
    0.58
    getT
    0.58
    ted
    0.57
    t
    0.50
    titia
    0.49
    TC
    0.49
    tableWidget
    0.49
    at
    0.47
    Act Density 0.571%

    No Known Activations