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

    Neuronpedia

    INDEX
    Explanations

    references to railway stations and their infrastructure

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

    Railways, trains, and rail-related infrastructure

    np_acts-logits-general · gemini-2.0-flash

    railway and train related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Medicaid
    -0.51
     nakalista
    -0.50
    tencent
    -0.47
    ulemon
    -0.46
     Alamo
    -0.45
    脲
    -0.45
     penthouse
    -0.45
    piram
    -0.45
     Rasmus
    -0.45
     necro
    -0.44
    POSITIVE LOGITS
     train
    1.68
     trains
    1.58
     railway
    1.56
     rail
    1.54
     Train
    1.51
     Trains
    1.46
    Train
    1.44
     Railway
    1.42
     Rail
    1.41
    Trains
    1.40
    Act Density 0.222%

    No Known Activations