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

    Neuronpedia

    INDEX
    Explanations

    Code-related text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    çijŁ
    -0.27
    çļĦéĩįçĤ¹
    -0.26
    umb
    -0.26
    èļķ
    -0.26
    åĿļæĮģ以
    -0.25
    ést
    -0.25
    caught
    -0.24
    æĺ¯ä»Ģä¹Īåij¢
    -0.24
    ista
    -0.24
    tap
    -0.24
    POSITIVE LOGITS
    )%
    0.27
    '%(
    0.26
    ynn
    0.26
    åįķè°ĥ
    0.26
    ]%
    0.26
     Integral
    0.25
     %↵↵
    0.24
    WAR
    0.24
     complement
    0.24
     Ways
    0.23
    Act Density 0.009%

    No Known Activations