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

    Neuronpedia

    INDEX
    Explanations

    elements related to films or literature, particularly their plots and characteristics

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

    book reviews and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.62
    rungsseite
    -0.57
    ########.
    -0.57
    ագրություններ
    -0.54
    __((
    -0.53
    內容簡介
    -0.52
    ANSA
    -0.52
     שוליים
    -0.52
    tvguidetime
    -0.51
    chelsea
    -0.51
    POSITIVE LOGITS
    RenderAtEndOf
    0.35
     Landwir
    0.35
    Autores
    0.31
     interesting
    0.31
    ală
    0.31
     Wochen
    0.30
    arrol
    0.30
     Entwick
    0.30
     exciting
    0.30
     creators
    0.29
    Act Density 0.058%

    No Known Activations