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

    Neuronpedia

    INDEX
    Explanations

    carbon dioxide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pples
    0.89
    gerald
    0.78
     Volumes
    0.76
    volumes
    0.72
    ppled
    0.69
     pleasure
    0.68
     critically
    0.68
    菇
    0.67
    pple
    0.67
     Broken
    0.65
    POSITIVE LOGITS
     dioxide
    2.56
     Dioxide
    2.11
     monoxide
    2.11
    dioxide
    1.95
    carbon
    1.46
    aceous
    1.42
     tetrachloride
    1.41
     डाइऑक्साइड
    1.40
    Carbon
    1.39
     carbon
    1.39
    Act Density 0.028%

    No Known Activations