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

    Neuronpedia

    INDEX
    Explanations

    Code libraries/configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Black
    -0.07
    ¹
    -0.07
     dys
    -0.07
     klin
    -0.06
    ('/',
    -0.06
     oxy
    -0.06
     chol
    -0.06
     zpráv
    -0.06
     ciddi
    -0.06
    ?]
    -0.06
    POSITIVE LOGITS
    .Fail
    0.06
    ẻ
    0.06
     Ext
    0.06
    plex
    0.06
    ulo
    0.06
    \DependencyInjection
    0.05
    NavLink
    0.05
     Sonia
    0.05
    	MD
    0.05
    动物
    0.05
    Act Density 0.057%

    No Known Activations