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

    Neuronpedia

    INDEX
    Explanations

    code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä¸ĢæľŁ
    -0.28
    ][:
    -0.28
    gings
    -0.26
    æķ¬ä¸ļ
    -0.25
    ä¸Ģé¡¿
    -0.24
     consume
    -0.24
    çļĦçIJĨ念
    -0.24
     treated
    -0.24
    çļĦè´¨éĩı
    -0.23
     break
    -0.23
    POSITIVE LOGITS
    çħ§
    0.29
    haft
    0.27
    etCode
    0.27
     buc
    0.27
    åĪ©
    0.27
    éģĵ
    0.26
     Classified
    0.26
    éĢĹ
    0.26
    æīįåıijçİ°
    0.25
    holes
    0.24
    Act Density 0.004%

    No Known Activations