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

    Neuronpedia

    INDEX
    Explanations

    technical language about how an automatic transmission works in car, especially a DSG

    oai_token-act-pair · gemini-2.0-flash

    technical car specifications

    np_token-act-pair-logits · gpt-4o-mini

    gearboxes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.00
     Anſ
    -0.98
     Houſe
    -0.97
     myſelf
    -0.93
     raiſ
    -0.91
     ſeveral
    -0.90
     Theſe
    -0.88
     preſent
    -0.88
     itſelf
    -0.87
     Efq
    -0.86
    POSITIVE LOGITS
     C
    0.60
     
    0.58
     co
    0.56
     au
    0.49
     Co
    0.47
     (
    0.46
      
    0.46
     R
    0.45
     K
    0.44
    -
    0.44
    Act Density 0.487%

    No Known Activations