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

    Neuronpedia

    INDEX
    Explanations

    references to dates and temporal expressions

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

    month of [month] or year with [location]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelves
    -0.65
    wiſe
    -0.64
    WebServlet
    -0.54
     ainfi
    -0.53
    ſelf
    -0.52
     Anſ
    -0.52
     Majefty
    -0.51
     ſche
    -0.50
     Verſ
    -0.49
     verſ
    -0.49
    POSITIVE LOGITS
    ufficio
    0.41
    ьаж
    0.40
    Източници
    0.40
     Wikimedijinoj
    0.39
    +:+
    0.37
    MemoryWarning
    0.37
    msgSender
    0.35
    uxxxx
    0.34
    ğimiz
    0.33
    ༘
    0.33
    Act Density 0.015%

    No Known Activations