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

    Neuronpedia

    INDEX
    Explanations

    Figure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cout
    -0.07
     geçmiş
    -0.07
    \Resources
    -0.07
     귀
    -0.07
     Thiên
    -0.07
     Butter
    -0.06
     Shelter
    -0.06
     reconciliation
    -0.06
     Brut
    -0.06
     contribution
    -0.06
    POSITIVE LOGITS
     chiar
    0.07
     disk
    0.06
    June
    0.06
     Did
    0.06
    EOF
    0.06
    (schema
    0.06
     japon
    0.06
     lash
    0.06
     equip
    0.06
    ARIO
    0.06
    Act Density 0.002%

    No Known Activations