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

    Neuronpedia

    INDEX
    Explanations

    code snippets including the word "Component" or "models"

    oai_token-act-pair · gemini-2.0-flash

    Component

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intptr
    -0.56
    diğini
    -0.54
     trast
    -0.54
    SpringBootTest
    -0.49
     comuniques
    -0.48
    errHandler
    -0.47
     numerus
    -0.47
     देते
    -0.47
     getCity
    -0.47
     omge
    -0.47
    POSITIVE LOGITS
    <bos>
    2.33
     برانيه
    0.65
     estimés
    0.63
    Хьажоргаш
    0.63
    orianCalendar
    0.62
    :][
    0.59
     الرياضيه
    0.56
     Савезне
    0.56
    ’
    0.55
    abetes
    0.54
    Act Density 0.080%

    No Known Activations