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

    Neuronpedia

    INDEX
    Explanations

    affordable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trat
    -0.08
     Cele
    -0.07
     Separ
    -0.07
     confid
    -0.07
     equipe
    -0.07
     Control
    -0.07
     control
    -0.07
     tratado
    -0.07
    inas
    -0.07
     treating
    -0.07
    POSITIVE LOGITS
     scour
    0.08
     mieszkań
    0.08
    建设
    0.08
     rooted
    0.08
    لىقى
    0.08
     dini
    0.08
     grounded
    0.07
     journalism
    0.07
     settlers
    0.07
     cortisol
    0.07
    Act Density 0.009%

    No Known Activations