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

    Neuronpedia

    INDEX
    Explanations

    Recycling codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     son's
    -0.08
    )&
    -0.08
     Steen
    -0.08
    Interested
    -0.08
    Prere
    -0.08
     cupid
    -0.08
     geïnteresse
    -0.08
    锋
    -0.08
    Ante
    -0.07
     interesado
    -0.07
    POSITIVE LOGITS
     beverage
    0.08
     контей
    0.08
    จ
    0.08
    ภ
    0.08
    supplier
    0.08
    สูง
    0.07
     bottle
    0.07
    ும்
    0.07
     numbered
    0.07
    โม
    0.07
    Act Density 0.007%

    No Known Activations