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

    Neuronpedia

    INDEX
    Explanations

    OneToMany

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сов
    -0.08
     SwiftUI
    -0.08
     amateur
    -0.07
    🐵
    -0.07
    .hs
    -0.07
     büyü
    -0.07
    "struct
    -0.07
    vio
    -0.07
    פרו
    -0.07
     tens
    -0.07
    POSITIVE LOGITS
    _SITE
    0.07
     drop
    0.07
     Father
    0.06
     fitted
    0.06
    	renderer
    0.06
    afa
    0.06
    wp
    0.06
    接待
    0.06
     entail
    0.06
     taper
    0.06
    Act Density 0.001%

    No Known Activations