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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kindergarten
    -0.08
     Communities
    -0.08
     principale
    -0.08
     Organizations
    -0.08
     Kenntnisse
    -0.07
    .Organization
    -0.07
     منظمة
    -0.07
     Tse
    -0.07
     &[
    -0.07
     Athletic
    -0.07
    POSITIVE LOGITS
     ambience
    0.09
     garder
    0.09
     sofa
    0.09
     ambiance
    0.08
     antique
    0.08
     antiques
    0.08
    家具
    0.08
     IKEA
    0.08
     लक
    0.08
     모습
    0.08
    Act Density 0.006%

    No Known Activations