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

    Neuronpedia

    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :error
    -0.07
    Deck
    -0.06
    릴
    -0.06
    anal
    -0.06
     пользователя
    -0.06
     пен
    -0.06
    Bar
    -0.06
     Бог
    -0.06
     Lov
    -0.06
     CEL
    -0.06
    POSITIVE LOGITS
     effort
    0.06
     undoubtedly
    0.06
    ovic
    0.06
     aquatic
    0.06
    èle
    0.06
    _sleep
    0.06
    iated
    0.06
     legislation
    0.06
     Royale
    0.06
     Brighton
    0.06
    Act Density 0.122%

    No Known Activations