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

    Neuronpedia

    INDEX
    Explanations

    terms related to efficiency and resource saving

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

    Cost or resource reduction

    np_acts-logits-general · gemini-2.0-flash

    reducing costs and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.70
     дописавши
    -0.63
    abestanden
    -0.59
    gación
    -0.55
     initComponents
    -0.54
    atguigu
    -0.53
    ंदीखरीदारी
    -0.52
     onPostExecute
    -0.51
    httphttps
    -0.51
    providedIn
    -0.50
    POSITIVE LOGITS
     costs
    0.82
     resources
    0.75
     unnecessary
    0.72
     resource
    0.71
     cost
    0.70
    costs
    0.68
     expense
    0.66
     expenditure
    0.66
     Costs
    0.64
     costly
    0.64
    Act Density 0.351%

    No Known Activations