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

    Neuronpedia

    INDEX
    Explanations

    Honda Civic and Integra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arbit
    0.43
    arly
    0.40
    鲇
    0.38
     marx
    0.38
     टेन
    0.37
    ists
    0.37
    挑
    0.36
    ellis
    0.36
     exercitation
    0.36
     advant
    0.35
    POSITIVE LOGITS
     integra
    0.58
     EG
    0.55
     civic
    0.55
     Integra
    0.54
     Civic
    0.53
    Si
    0.53
     integrals
    0.52
    Civ
    0.52
    Prel
    0.50
     EK
    0.50
    Act Density 0.003%

    No Known Activations