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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ')])↵
    -0.07
    (dummy
    -0.07
    esterday
    -0.06
     Sapphire
    -0.06
    ем
    -0.06
    (viewModel
    -0.06
     Granny
    -0.06
    燚
    -0.06
     chương
    -0.06
    能量
    -0.06
    POSITIVE LOGITS
     annotations
    0.07
     produção
    0.07
     Personen
    0.07
     Oven
    0.07
     maritime
    0.07
    ẓ
    0.07
     zo
    0.07
    -fat
    0.07
     새로
    0.07
     לצאת
    0.07
    Act Density 0.021%

    No Known Activations