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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lesions
    -0.07
     Regional
    -0.07
     pole
    -0.06
     Stage
    -0.06
     번째
    -0.06
    ')):↵
    -0.06
     Christians
    -0.06
     leicht
    -0.06
     endpoints
    -0.06
     Moore
    -0.06
    POSITIVE LOGITS
    crast
    0.07
     AG
    0.07
     취
    0.07
     décou
    0.07
    ,lat
    0.06
    FullScreen
    0.06
     куп
    0.06
     최
    0.06
     jogador
    0.06
    amm
    0.06
    Act Density 0.023%

    No Known Activations