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

    Neuronpedia

    INDEX
    Explanations

    Legion/ion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .keyword
    -0.07
     alanda
    -0.06
    _smooth
    -0.06
     stance
    -0.06
    kee
    -0.06
    iks
    -0.06
     TOTAL
    -0.06
    %c
    -0.06
     Barker
    -0.06
     Transportation
    -0.05
    POSITIVE LOGITS
     Legion
    0.24
     legion
    0.17
     lég
    0.15
     Federation
    0.07
     Fus
    0.07
     Cic
    0.07
    ION
    0.07
     Hedge
    0.07
    ion
    0.07
     Countdown
    0.07
    Act Density 0.002%

    No Known Activations