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

    Neuronpedia

    INDEX
    Explanations

    government

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ange
    -0.07
    heim
    -0.06
     abb
    -0.06
     Ved
    -0.06
    ете
    -0.06
     Ev
    -0.06
     guardian
    -0.06
    ses
    -0.06
     buggy
    -0.06
     Clan
    -0.06
    POSITIVE LOGITS
    ิดต
    0.07
    Scalars
    0.07
     helium
    0.06
    Special
    0.06
     Республи
    0.06
    onium
    0.06
     fırsat
    0.06
     چگونه
    0.06
     전용
    0.06
     medals
    0.06
    Act Density 0.323%

    No Known Activations