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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to records or significant historical events

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

    biggest history ever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     žem
    -0.36
     вовсе
    -0.35
     urbanas
    -0.32
     fijo
    -0.32
     box
    -0.30
     beads
    -0.30
     aukš
    -0.30
     sisters
    -0.29
     abstrait
    -0.29
     keramik
    -0.28
    POSITIVE LOGITS
    ISupport
    0.64
    BufferException
    0.59
    المشاركات
    0.59
    SharedCtor
    0.56
     للاسماء
    0.54
    magnitude
    0.53
     magnitude
    0.53
     ProtoMessage
    0.52
    RequiresApi
    0.50
    SharedDtor
    0.49
    Act Density 0.012%

    No Known Activations