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

    Neuronpedia

    INDEX
    Explanations

    BuilderFactory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Judy
    -0.07
     Lol
    -0.06
     Stage
    -0.06
    Community
    -0.06
    izo
    -0.06
     Пло
    -0.06
    альная
    -0.06
    actice
    -0.06
    Mean
    -0.06
    mult
    -0.06
    POSITIVE LOGITS
    /xhtml
    0.07
     Fond
    0.07
     ανά
    0.06
    Atlanta
    0.06
     än
    0.06
     loyal
    0.06
     özg
    0.06
     и
    0.06
     กรก
    0.06
     싸
    0.06
    Act Density 0.005%

    No Known Activations