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

    Neuronpedia

    INDEX
    Explanations

    either/or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    น
    0.45
     reaper
    0.44
    সম্মত
    0.44
     columns
    0.41
     Temperature
    0.41
     experto
    0.40
    _
    0.40
     ListNode
    0.40
     нанесе
    0.39
     Limerick
    0.39
    POSITIVE LOGITS
     inklusive
    0.50
    েন্ড
    0.46
    klus
    0.46
    ﱢ
    0.46
    enuine
    0.44
    FAX
    0.44
    𝗲
    0.44
    جراء
    0.43
    andin
    0.42
    BON
    0.42
    Act Density 0.001%

    No Known Activations