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

    Neuronpedia

    INDEX
    Explanations

    sections of text that indicate ongoing or continuing actions

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

    related to language identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.70
    XmlAccessorType
    -0.55
     فريبيس
    -0.52
     تضيفلها
    -0.51
     Wikimedijinoj
    -0.50
    ьаж
    -0.49
     يتيمه
    -0.48
     kasarigan
    -0.47
     المعيارى
    -0.45
    |()
    -0.44
    POSITIVE LOGITS
     dyr
    0.52
    oa̍t
    0.47
     pierna
    0.44
    árbol
    0.43
    Whitelist
    0.42
     prácti
    0.42
    protetor
    0.42
    ########.
    0.41
    ierna
    0.40
     priorité
    0.40
    Act Density 0.370%

    No Known Activations