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

    Neuronpedia

    INDEX
    Explanations

    words indicating existence or states of being

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

    numbers and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.42
    Skocz
    -0.40
     المعيارى
    -0.39
    isait
    -0.36
    transQ
    -0.36
     multi
    -0.36
    studied
    -0.35
     cherchés
    -0.35
     gått
    -0.35
    ies
    -0.34
    POSITIVE LOGITS
     ControllerBase
    0.52
    хьтан
    0.49
     EconPapers
    0.47
    ollectionView
    0.42
     Kombat
    0.42
    Rptr
    0.41
     upvote
    0.41
    angliski
    0.41
    rosoft
    0.40
     ✭✭
    0.40
    Act Density 0.034%

    No Known Activations