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

    Neuronpedia

    INDEX
    Explanations

    dependency declaration and System assembly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     renaming
    0.30
     onPressed
    0.29
    üyada
    0.29
    嘈
    0.28
    pertensive
    0.28
    estructura
    0.28
    𝑭
    0.28
     restricting
    0.28
    新能源
    0.28
    ά
    0.27
    POSITIVE LOGITS
     Condition
    0.30
     حا
    0.29
    van
    0.29
     Vogel
    0.28
    िक
    0.27
    Nun
    0.27
     ADMINISTRATION
    0.27
     ван
    0.26
     Dai
    0.26
     கடை
    0.26
    Act Density 0.000%

    No Known Activations