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

    Neuronpedia

    INDEX
    Explanations

    references to television shows and their episodes

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

    guest stars on TV shows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.45
    exitRule
    -0.44
     nonUne
    -0.44
    ModelForm
    -0.41
     AssemblyCulture
    -0.39
     Савезне
    -0.39
     hObject
    -0.38
     placed
    -0.36
     Taktlose
    -0.36
    InteropServices
    -0.36
    POSITIVE LOGITS
     Jefus
    0.50
     Monfieur
    0.49
     ſche
    0.49
     deſt
    0.47
    Fernsehserie
    0.47
    neté
    0.47
     houſe
    0.47
    damente
    0.46
     myſelf
    0.46
     ſch
    0.45
    Act Density 0.005%

    No Known Activations