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

    Neuronpedia

    INDEX
    Explanations

    references to TV shows and movies

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

    TV and television

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    حياته
    -0.42
     en
    -0.40
    spre
    -0.40
    neuri
    -0.39
     chắn
    -0.38
     Schröder
    -0.38
     ende
    -0.37
    delimiter
    -0.37
    ende
    -0.37
     sempre
    -0.37
    POSITIVE LOGITS
     TV
    1.05
     Television
    1.05
     telewiz
    0.99
    television
    0.99
     television
    0.98
     televisions
    0.96
     télévision
    0.96
    Television
    0.95
     tv
    0.94
     televisión
    0.93
    Act Density 0.018%

    No Known Activations