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

    Neuronpedia

    INDEX
    Explanations

    `sys` module import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dall
    0.42
     Alt
    0.40
    ZZ
    0.38
    кия
    0.38
    官
    0.38
     organics
    0.38
     separable
    0.37
     alt
    0.37
     brisket
    0.37
     చా
    0.37
    POSITIVE LOGITS
     sys
    0.99
    sys
    0.85
     SYS
    0.61
    Sys
    0.59
     script
    0.57
    argc
    0.56
     Sys
    0.56
     systemic
    0.55
    argv
    0.54
     argc
    0.51
    Act Density 0.007%

    No Known Activations