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

    Neuronpedia

    INDEX
    Explanations

    automotive specifications and features

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

    Car comfort and performance

    np_acts-logits-general · gemini-2.0-flash

    positive vehicle attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.73
    ThroughAttribute
    -0.63
    rungsseite
    -0.61
    apimachinery
    -0.60
    SocketChannel
    -0.58
    enschappelijke
    -0.57
     MenuView
    -0.55
    ValueGenerated
    -0.51
     kran
    -0.51
    ריאה
    -0.50
    POSITIVE LOGITS
     comfort
    0.93
     handling
    0.75
     performance
    0.72
     comfortable
    0.72
     COMFORT
    0.70
     comforts
    0.70
     Handling
    0.69
    Refinement
    0.69
     refinement
    0.69
     Comfort
    0.67
    Act Density 0.132%

    No Known Activations