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

    Neuronpedia

    INDEX
    Explanations

    Politics/Government

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .mat
    -0.07
     trail
    -0.07
    ілі
    -0.06
     rolled
    -0.06
     cli
    -0.06
    stractions
    -0.06
    protocols
    -0.06
    Mutable
    -0.06
    	sc
    -0.06
    (SC
    -0.06
    POSITIVE LOGITS
    /www
    0.07
     Subscribe
    0.07
    \Common
    0.07
     contrario
    0.07
     Пост
    0.07
    OfBirth
    0.06
    Memo
    0.06
     pageTitle
    0.06
     ±
    0.06
     unreliable
    0.06
    Act Density 0.174%

    No Known Activations