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

    Neuronpedia

    INDEX
    Explanations

    CO2 equivalent or dioxide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oxide
    0.65
     oxides
    0.61
     dioxide
    0.52
     monoxide
    0.46
     carbon
    0.45
    dioxide
    0.45
     ऑक्साइड
    0.44
     Oxide
    0.44
    蒸
    0.43
     carbonate
    0.42
    POSITIVE LOGITS
    っぱり
    0.42
    विड़
    0.41
     তদ
    0.41
    лое
    0.40
    torn
    0.38
    িলাম
    0.37
    tku
    0.37
    ptăm
    0.37
     antiseptic
    0.37
    িপুর
    0.37
    Act Density 0.008%

    No Known Activations