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

    Neuronpedia

    INDEX
    Explanations

    code structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आमतौर
    0.29
    rifugal
    0.29
     화학
    0.28
     வெப்ப
    0.28
     употреб
    0.28
     소개
    0.27
     воспа
    0.27
     سرطان
    0.27
    GLAND
    0.27
     ಸಾಮಾನ್ಯವಾಗಿ
    0.27
    POSITIVE LOGITS
    (),
    0.33
     '',
    0.32
     [],
    0.31
     will
    0.31
     d
    0.30
     "",
    0.29
    ,
    0.28
     all
    0.27
     only
    0.27
    "",
    0.27
    Act Density 0.212%

    No Known Activations