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

    Neuronpedia

    INDEX
    Explanations

    federal government entities and programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oslo
    0.38
     মানুষদের
    0.38
     Hamming
    0.38
    波动
    0.37
     adiabatically
    0.37
    ying
    0.37
    虾
    0.36
     দিকে
    0.35
     forefront
    0.35
     topLeft
    0.35
    POSITIVE LOGITS
    government
    0.64
     government
    0.61
    Government
    0.53
     सरकार
    0.51
    wide
    0.51
    सरकार
    0.49
    Feder
    0.48
    WIDE
    0.48
    Fed
    0.46
    Wide
    0.45
    Act Density 0.009%

    No Known Activations