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

    Neuronpedia

    INDEX
    Explanations

    concepts related to combination or merging of elements

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

    merging or blending together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.48
     pember
    -0.43
     المعيارى
    -0.43
    reide
    -0.41
    ExecuteReader
    -0.41
    indication
    -0.41
     perforation
    -0.40
    didSet
    -0.40
     اط
    -0.40
    おか
    -0.39
    POSITIVE LOGITS
     blending
    1.07
     merging
    1.02
     blended
    0.98
     blend
    0.93
     merge
    0.92
     merges
    0.90
     merged
    0.86
     fusion
    0.85
     blends
    0.85
     fusing
    0.84
    Act Density 0.020%

    No Known Activations