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

    Neuronpedia

    INDEX
    Explanations

    mathematical or scientific notation related to differential operators

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

    gradient operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uksessa
    -0.48
     otomatig
    -0.45
     méri
    -0.44
    Sheet
    -0.44
    sheet
    -0.44
    anggap
    -0.44
     елның
    -0.44
    tablissements
    -0.43
     eksemp
    -0.42
    PARTS
    -0.42
    POSITIVE LOGITS
    nabla
    2.53
    ∇
    1.70
    0.68
     ▼
    0.60
    lacian
    0.59
    nab
    0.55
    grad
    0.55
     gradient
    0.48
    gradient
    0.47
    naver
    0.47
    Act Density 0.010%

    No Known Activations