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

    Neuronpedia

    INDEX
    Explanations

    her

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zufrieden
    -0.10
     triglycer
    -0.08
     Konkurrenz
    -0.08
     Scha
    -0.08
     Schluss
    -0.08
     picky
    -0.08
     Dhabi
    -0.08
     trape
    -0.08
     prestations
    -0.08
     weird
    -0.08
    POSITIVE LOGITS
     insurg
    0.19
     militant
    0.17
     rebel
    0.16
     rebels
    0.16
     activist
    0.15
     activism
    0.15
     rebellion
    0.15
     protest
    0.14
     activists
    0.14
     guerr
    0.14
    Act Density 0.107%

    No Known Activations