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

    Neuronpedia

    INDEX
    Explanations

    references to railway stations and related infrastructure

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

    railway station

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ben
    -0.47
    Dean
    -0.47
    Damon
    -0.46
    Vince
    -0.45
    demand
    -0.44
    Gus
    -0.44
    Gabe
    -0.44
    Nick
    -0.43
    Don
    -0.43
    Joe
    -0.42
    POSITIVE LOGITS
     Railway
    1.89
     railway
    1.84
     RAILWAY
    1.74
    Railway
    1.73
    railway
    1.72
     railways
    1.63
     Railways
    1.53
     railroad
    1.35
     ferrocarril
    1.32
     Railroad
    1.27
    Act Density 0.006%

    No Known Activations