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

    Neuronpedia

    INDEX
    Explanations

    references to wheels and wheel-related terminology

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

    driving wheels and the fourth wall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prägt
    -0.33
     kuten
    -0.30
    řeba
    -0.29
     Bibliothek
    -0.29
     rangement
    -0.28
     اط
    -0.28
    start
    -0.28
    到
    -0.28
     naman
    -0.28
     Architektur
    -0.28
    POSITIVE LOGITS
    WriteTagHelper
    0.88
    ſelves
    0.84
    wheel
    0.81
     мәкал
    0.80
    wheeler
    0.78
     autorytatywna
    0.75
    ftagPool
    0.75
    الحياه
    0.74
    GEBURTSDATUM
    0.70
    Wheel
    0.70
    Act Density 0.008%

    No Known Activations